I
n
t
e
r
n
at
ion
al
Jou
r
n
al
of
E
lec
t
r
ical
an
d
Com
p
u
t
e
r
E
n
gin
e
e
r
in
g
(
I
JE
CE
)
Vol.
1
4
,
No.
5
,
Oc
tober
20
2
4
,
pp
.
6047
~
6056
I
S
S
N:
2088
-
8708
,
DO
I
:
10
.
11591/i
jec
e
.
v
1
4
i
5
.
pp
6
047
-
6056
6047
Jou
r
n
al
h
omepage
:
ht
tp:
//
ij
e
c
e
.
iaes
c
or
e
.
c
om
C
lo
u
d
b
ase
d
p
r
e
d
i
c
t
io
n
o
f
e
p
il
e
p
t
ic
s
e
iz
u
r
e
s u
si
n
g
r
e
al
-
t
ime
e
le
c
t
r
o
e
n
c
e
p
h
al
ogr
a
m
s
a
n
al
y
si
s
Gou
s
ia
T
h
ah
n
iyat
h
1
,
Chellu
b
oin
a
S
u
b
b
ar
ayu
d
u
Gan
gaiah
Yadav
2
,
Ra
j
agop
alan
S
e
n
k
am
a
laval
l
i
3
,
S
h
an
m
u
gam
S
a
t
h
iya
P
r
iya
4
,
S
t
ali
n
Aghal
ya
5
,
K
u
p
p
ire
d
d
y
Nar
s
im
h
a
Re
d
d
y
6
,
S
u
b
b
iah
M
u
r
u
ga
n
7
1
D
e
pa
r
tm
e
nt
of
C
omput
e
r
S
c
ie
nc
e
a
nd E
ngi
ne
e
r
in
g, D
a
ya
n
a
nda
S
a
ga
r
U
ni
ve
r
s
it
y,
B
a
nga
lo
r
e
, I
ndi
a
2
D
e
pa
r
tm
e
nt
of
E
le
c
tr
oni
c
s
a
nd C
omm
uni
c
a
ti
on E
ngi
ne
e
r
in
g, C
ha
it
a
nya
B
ha
r
a
th
i
I
ns
ti
tu
te
of
T
e
c
hnol
ogy, Andhr
a
P
r
a
de
s
h, I
ndi
a
3
D
e
pa
r
tm
e
nt
of
C
omput
e
r
S
c
ie
nc
e
a
nd E
ngi
ne
e
r
in
g, K
a
mm
a
va
r
i
S
a
ngha
m I
ns
ti
tu
te
of
T
e
c
hnol
ogy, B
a
nga
lo
r
e
, I
ndi
a
4
D
e
pa
r
tm
e
nt
of
E
le
c
tr
oni
c
s
a
nd C
omm
uni
c
a
ti
on E
ngi
ne
e
r
in
g, P
a
ni
ma
la
r
E
ngi
ne
e
r
in
g C
ol
le
ge
, C
he
nna
i,
I
ndi
a
5
D
e
pa
r
tm
e
nt
of
E
le
c
tr
oni
c
s
a
nd C
omm
uni
c
a
ti
on E
ngi
ne
e
r
in
g, S
t.
J
os
e
ph’
s
C
ol
le
g
e
of
E
ngi
ne
e
r
in
g, C
he
nna
i,
I
ndi
a
6
D
e
pa
r
tm
e
nt
of
E
le
c
tr
oni
c
s
a
nd C
omm
uni
c
a
ti
on E
ngi
ne
e
r
in
g, V
a
r
dha
ma
n C
ol
le
ge
of
E
ngi
ne
e
r
in
g, H
yde
r
a
ba
d, I
ndi
a
7
D
e
pa
r
tm
e
nt
of
B
io
me
di
c
a
l
E
ngi
ne
e
r
in
g, S
a
ve
e
th
a
S
c
hool
of
E
ngi
ne
e
r
in
g, S
a
ve
e
th
a
I
ns
ti
tu
te
of
M
e
di
c
a
l
a
nd
T
e
c
hni
c
a
l
S
c
ie
nc
e
s
,
S
a
ve
e
th
a
U
ni
ve
r
s
it
y, C
he
nn
a
i,
I
ndi
a
Ar
t
icle
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
ived
J
a
n
22,
2024
R
e
vis
e
d
J
ul
5,
2024
Ac
c
e
pted
J
ul
9,
2024
T
h
i
s
s
t
u
d
y
ai
ms
t
o
i
mp
ro
v
e
t
h
e
accu
r
acy
o
f
ep
i
l
ep
t
i
c
s
ei
zu
re
p
red
i
ct
i
o
n
u
s
i
n
g
cl
o
u
d
-
b
as
ed
,
real
-
t
i
me
el
ect
ro
en
c
ep
h
al
o
g
ram
an
a
l
y
s
i
s
.
T
h
e
g
o
al
i
s
t
o
b
u
i
l
d
a
s
t
ro
n
g
framew
o
rk
t
h
at
can
q
u
i
ck
l
y
p
ro
ces
s
el
ect
ro
en
cep
h
al
o
g
ram
(E
E
G
)
d
at
a,
ex
t
ra
ct
rel
ev
an
t
feat
u
res
,
an
d
u
s
e
ad
v
an
c
ed
mach
i
n
e
l
earn
i
n
g
al
g
o
ri
t
h
ms
t
o
p
red
i
ct
s
ei
zu
res
w
i
t
h
h
i
g
h
accu
racy
an
d
l
o
w
l
at
en
cy
b
y
t
ak
i
n
g
ad
v
an
t
ag
e
o
f
cl
o
u
d
p
l
at
fo
rms
'
co
mp
u
t
i
n
g
p
o
w
er
an
d
s
cal
ab
i
l
i
t
y
.
T
h
e
mai
n
o
b
j
ect
i
v
e
i
s
t
o
p
ro
v
i
d
e
p
at
i
en
t
s
an
d
t
h
ei
r
ca
re
g
i
v
ers
w
i
t
h
t
i
mel
y
n
o
t
i
fi
cat
i
o
n
s
s
o
t
h
at
t
h
ey
may
co
n
t
ro
l
ep
i
l
ep
s
y
ep
i
s
o
d
es
p
ro
act
i
v
el
y
.
T
h
e
g
o
al
o
f
t
h
i
s
p
ro
j
ect
i
s
t
o
i
mp
ro
v
e
t
h
e
l
i
v
es
o
f
p
eo
p
l
e
w
i
t
h
ep
i
l
ep
s
y
b
y
red
u
ci
n
g
t
h
e
i
mp
act
o
f
s
ei
zu
res
an
d
i
mp
ro
v
i
n
g
t
reat
m
en
t
res
u
l
t
s
v
i
a
r
eal
-
t
i
me
an
al
y
s
i
s
o
f
E
E
G
d
at
a.
Cl
o
u
d
co
mp
u
t
i
n
g
al
s
o
a
l
l
o
w
s
t
h
e
s
u
g
g
es
t
ed
s
ei
zu
re
p
red
i
ct
i
o
n
s
y
s
t
em
t
o
b
e
mo
re
acces
s
i
b
l
e
an
d
s
c
a
l
ab
l
e,
me
an
i
n
g
mo
re
p
eo
p
l
e
w
o
rl
d
w
i
d
e
co
u
l
d
b
en
efi
t
fro
m
i
t
.
T
h
i
s
s
ect
i
o
n
d
i
s
cu
s
s
es
t
h
e
res
u
l
t
s
fro
m
fi
v
e
s
ep
ar
at
e
d
at
as
et
s
o
f
p
at
i
en
t
s
w
i
t
h
ep
i
l
ep
t
i
c
s
ei
zu
res
w
h
o
u
n
d
erw
en
t
E
E
G
an
al
y
s
i
s
w
i
t
h
t
h
e
fo
l
l
o
w
i
n
g
d
et
ai
l
s
as
fro
n
t
o
p
o
l
ar
(FP1
,
FP2
),
fro
n
t
a
l
(F3
,
F4
)
,
fro
n
t
o
t
emp
o
ral
(F7
,
F8
),
c
en
t
ral
(C3
,
C4
),
t
emp
o
ral
(T
3
,
T
4
),
p
ari
et
o
-
t
emp
o
ral
(T
5
,
T
6
)
,
p
a
ri
et
al
(
P3
,
P4
),
o
cci
p
i
t
al
(O
1
,
O
2
),
t
i
me
(H
H
:
MM:
SS)
.
K
e
y
w
o
r
d
s
:
C
loud
c
omput
ing
E
lec
tr
oe
nc
e
pha
logr
a
ms
a
na
lys
is
E
pil
e
pti
c
s
e
izur
e
pr
e
diction
I
ntelli
ge
nt
he
a
lt
hc
a
r
e
s
ys
tems
S
ignal
pr
oc
e
s
s
ing
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
ce
n
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
Gous
ia
T
ha
hniyath
De
pa
r
tm
e
nt
of
C
omput
e
r
S
c
ienc
e
a
nd
E
nginee
r
ing
,
Da
ya
na
nda
S
a
ga
r
Unive
r
s
it
y
I
nnova
ti
on
C
a
mpus
,
Kudlu
Ga
te
,
Hos
ur
M
a
in
R
oa
d,
B
a
nga
lor
e
,
Ka
r
na
taka
,
I
nd
ia
E
mail:
gous
ia
-
c
s
e
@ds
u.
e
du.
in
1.
I
NT
RODU
C
T
I
ON
T
h
is
r
e
s
e
a
r
c
h
a
im
s
t
o
p
r
ov
id
e
a
ne
w
m
e
t
ho
d
f
o
r
f
o
r
e
c
a
s
t
in
g
e
p
il
e
p
ti
c
s
e
izu
r
e
s
b
y
a
na
ly
z
i
ng
e
le
c
t
r
o
e
n
c
e
p
ha
lo
g
r
a
m
(
E
E
G
)
da
ta
in
r
e
a
l
-
ti
me
on
t
he
c
l
ou
d
.
T
he
un
p
r
e
di
c
ta
b
il
it
y
o
f
e
p
il
e
ps
y
,
a
n
e
u
r
o
l
og
ica
l
i
l
ln
e
s
s
m
a
r
ke
d
by
r
e
pe
a
te
d
c
on
vu
ls
io
ns
,
c
a
us
e
s
s
ubs
tan
t
ia
l
h
a
r
ds
h
i
p
f
o
r
th
os
e
a
f
f
li
c
te
d
.
T
im
e
l
y
i
n
te
r
ve
n
t
io
n
a
nd
b
e
t
te
r
pa
ti
e
n
t
o
u
tco
mes
ma
y
be
a
c
h
ie
ve
d
w
it
h
e
a
r
l
y
s
e
iz
u
r
e
p
r
e
d
ic
ti
on
.
A
n
E
E
G
p
r
e
d
ic
ti
on
m
od
e
l
t
h
a
t
c
a
n
i
de
n
ti
f
y
p
r
e
ic
ta
l
(
p
e
r
i
od
im
me
d
iat
e
l
y
be
f
o
r
e
a
s
e
iz
ur
e
oc
c
u
r
s
)
r
h
yt
hm
s
is
o
ur
g
oa
l
,
a
nd
we
w
a
n
t
to
a
c
hi
e
v
e
th
i
s
b
y
us
i
ng
r
e
c
e
n
t
d
e
ve
lo
p
men
ts
in
c
lo
ud
c
o
mp
ut
in
g
a
nd
ma
c
h
in
e
lea
r
ni
ng
.
Ou
r
m
is
s
i
on
is
to
d
e
ve
lo
p
a
r
e
a
l
-
ti
me
E
E
G
da
t
a
a
n
a
l
ys
is
to
ol
tha
t
m
a
y
h
e
l
p
pe
op
le
w
it
h
e
pi
le
ps
y
,
the
i
r
l
ov
e
d
o
ne
s
,
a
nd
m
e
d
ica
l
p
r
of
e
s
s
i
on
a
l
s
be
tt
e
r
p
r
e
pa
r
e
f
o
r
a
nd
r
e
s
po
nd
to
s
e
i
z
u
r
e
e
p
is
o
de
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
1
4
,
No.
5
,
Oc
tober
2
02
4
:
6047
-
6056
6048
O
u
r
s
t
ud
y's
ma
in
c
on
t
r
i
bu
t
io
n
is
i
n
teg
r
a
t
in
g
c
lo
u
d
-
ba
s
e
d
i
n
f
r
a
s
tr
uc
tu
r
e
wi
th
a
d
va
n
c
e
d
ma
c
h
in
e
l
e
a
r
ni
ng
a
l
go
r
it
hms
de
s
ig
ne
d
f
o
r
E
E
G
a
n
a
l
ys
is
.
W
e
a
im
to
a
d
d
r
e
s
s
th
e
d
r
a
wba
c
ks
o
f
c
on
ve
n
t
io
na
l
s
e
iz
u
r
e
p
r
e
d
ic
ti
on
me
th
ods
,
s
uc
h
a
s
t
he
i
r
r
e
l
ian
c
e
o
n
o
f
f
l
i
ne
p
r
oc
e
s
s
i
ng
a
nd
lac
k
o
f
r
e
a
l
-
t
i
me
c
a
pa
bi
li
t
ies
,
b
y
us
in
g
c
lo
ud
p
la
t
f
o
r
ms
'
s
c
a
la
b
il
it
y
a
n
d
c
o
mp
ut
in
g
c
a
pa
c
it
y
.
I
n
a
dd
i
ti
on
,
o
u
r
me
th
od
is
de
s
i
gn
e
d
t
o
ta
c
k
le
t
he
is
s
ue
o
f
ta
i
lo
r
e
d
s
e
iz
u
r
e
p
r
e
d
ict
i
on
mo
de
ls
t
ha
t
c
o
ns
i
de
r
t
ha
t
e
a
c
h
pe
r
s
on
's
E
E
G
p
a
t
te
r
n
s
a
n
d
s
e
izu
r
e
dy
na
mi
c
s
a
r
e
un
iq
ue
.
W
e
a
r
e
a
d
d
in
g
e
le
men
ts
l
ike
pa
t
ien
t
-
s
p
e
c
if
ic
da
ta
a
n
d
a
da
pt
i
ve
lea
r
ni
ng
me
th
od
s
t
o
mak
e
o
u
r
p
r
e
d
ic
ti
on
e
ng
ine
m
o
r
e
a
c
c
u
r
a
te
a
n
d
r
e
l
iab
le
.
B
y
s
h
ow
in
g
th
a
t
c
lou
d
-
b
a
s
e
d
p
r
e
d
ic
ti
ve
a
n
a
l
yt
ics
f
o
r
ne
ur
ol
og
ic
a
l
i
l
ln
e
s
s
e
s
is
f
e
a
s
i
bl
e
a
n
d
us
e
f
ul
,
ou
r
s
tu
dy
h
a
s
t
he
r
a
pe
ut
ic
im
pl
ic
a
t
io
ns
a
nd
a
dds
to
he
a
lt
hc
a
r
e
i
n
f
o
r
m
a
t
ics
.
One
o
f
o
u
r
l
on
g
-
t
e
r
m
goa
ls
i
s
to
im
p
r
o
ve
t
he
a
c
c
e
s
s
ib
i
li
ty
a
nd
us
e
f
u
ln
e
s
s
o
f
s
e
iz
ur
e
p
r
e
di
c
t
io
n
t
oo
ls
b
y
in
te
g
r
a
ti
ng
th
e
m
in
to
c
u
r
r
e
n
t
h
e
a
l
t
hc
a
r
e
in
f
r
a
s
t
r
u
c
t
u
r
e
a
nd
m
a
k
in
g
t
he
m
a
va
il
a
b
le
r
e
mo
te
ly
us
i
ng
c
lo
ud
c
o
mp
ut
in
g
.
T
h
is
w
il
l
be
n
e
f
it
p
a
t
ie
nts
a
l
l
ove
r
th
e
g
lo
be
.
O
u
r
e
f
f
or
t
a
i
ms
t
o
p
r
ov
id
e
a
c
lo
ud
-
ba
s
e
d
pla
t
f
o
r
m
f
o
r
r
e
a
l
-
t
im
e
E
E
G
a
na
l
ys
is
to
i
mp
r
ove
c
ur
r
e
n
t
m
e
th
ods
f
o
r
p
r
e
d
ict
i
ng
e
pi
le
pt
ic
s
e
iz
u
r
e
s
.
O
ur
go
a
l
is
t
o
i
mp
r
ov
e
th
e
l
iv
e
s
o
f
pe
op
le
w
i
th
e
pi
le
ps
y
b
y
de
v
e
l
op
i
ng
a
s
c
a
la
bl
e
a
n
d
e
f
f
e
c
t
iv
e
s
ol
u
ti
on
f
o
r
e
a
r
l
y
s
e
i
z
u
r
e
d
e
t
e
c
t
i
on
us
in
g
c
l
ou
d
c
o
mp
ut
in
g
a
n
d
mac
hi
ne
le
a
r
n
in
g
m
e
th
ods
.
T
he
r
e
s
t
o
f
t
he
pa
pe
r
is
o
r
ga
niz
e
d
a
s
r
e
a
l
-
t
i
me
E
E
G
a
n
a
l
ys
is
f
o
r
e
pi
le
pt
ic
s
e
iz
ur
e
s
is
s
u
mm
a
r
ize
d
i
n
s
e
c
t
io
n
2
.
S
e
c
t
io
n
3
s
ho
ws
t
he
ou
tc
omes
o
f
a
pp
ly
ing
t
he
E
E
G
a
na
lys
is
pa
r
a
me
te
r
s
t
o
f
i
ve
pa
t
e
n
ts
w
it
h
v
a
r
y
in
g
t
i
mi
ngs
.
T
he
las
t
s
e
c
t
io
n
,
s
e
c
t
io
n
4
,
pr
e
s
e
nts
th
e
c
o
nc
lus
i
on
.
C
ut
ti
ng
-
e
d
ge
te
c
h
no
lo
gy
h
a
s
im
p
r
o
ve
d
n
e
u
r
ol
og
ica
l
d
is
e
a
s
e
t
he
r
a
py
.
M
i
l
li
ons
w
or
l
dw
ide
s
u
f
f
e
r
f
r
o
m
e
pi
le
ps
y
,
a
ne
ur
ol
og
ic
a
l
il
ln
e
s
s
t
ha
t
c
a
us
e
s
s
e
izu
r
e
s
.
E
p
il
e
p
ti
c
e
p
is
o
de
s
mus
t
be
p
r
e
d
ic
te
d
e
a
r
ly
a
nd
a
c
c
u
r
a
tel
y
f
o
r
e
f
f
e
c
ti
ve
t
r
e
a
t
men
t
a
n
d
q
ua
li
t
y
o
f
l
if
e
.
C
onv
e
n
t
io
na
l
E
E
G
a
na
ly
s
is
me
th
od
s
h
a
ve
l
im
i
te
d
r
e
a
l
-
ti
me
p
r
oc
e
s
s
i
ng
a
nd
pr
e
d
ic
ti
ng
a
c
c
ur
a
c
y
[
1
]
.
Du
e
t
o
r
a
p
id
a
d
va
n
c
e
s
in
c
lo
ud
c
om
pu
t
in
g
,
i
ma
ge
p
r
oc
e
s
s
in
g
,
a
n
d
s
i
gn
a
l
p
r
oc
e
s
s
i
ng
,
e
p
i
lep
t
ic
s
e
i
z
u
r
e
p
r
e
di
c
t
io
n
ha
s
c
h
a
n
ge
d
.
C
lo
ud
c
o
mp
u
ti
ng
f
o
r
r
e
a
l
-
ti
me
E
E
G
mo
ni
to
r
in
g
i
m
p
r
o
ve
s
s
e
iz
u
r
e
pr
e
d
ic
ti
on
i
n
e
pi
le
ps
y
pa
t
ien
ts
by
us
in
g
c
ut
t
in
g
-
e
d
ge
i
ma
ge
a
nd
s
i
gna
l
p
r
oc
e
s
s
i
ng
.
T
h
is
r
e
s
e
a
r
c
h
us
e
s
c
lo
ud
-
ba
s
e
d
tec
hn
ol
og
y
t
o
i
m
pr
ov
e
e
pi
le
ps
y
c
a
r
e
b
y
p
r
e
d
ic
ti
ng
mo
r
e
a
c
c
u
r
a
te
ly
a
nd
qu
ic
k
ly
[
2
]
.
T
h
e
a
bi
l
it
y
t
o
e
las
ti
c
a
ll
y
a
c
c
e
s
s
da
ta
a
n
d
p
r
oc
e
s
s
in
g
p
owe
r
ha
s
ma
de
c
l
ou
d
c
om
pu
ti
ng
a
ba
s
i
c
t
e
c
hn
ol
og
y
.
I
ts
med
ic
a
l
us
a
g
e
ha
s
e
na
b
led
s
ubs
ta
nt
i
a
l
a
dv
a
nc
e
m
e
n
t
.
M
e
d
ic
a
l
pr
o
f
e
s
s
io
na
ls
m
a
y
s
e
c
u
r
e
ly
s
a
ve
h
u
ge
E
E
G
da
ta
o
n
th
e
c
l
ou
d
f
o
r
wo
r
l
dw
id
e
da
ta
in
te
r
c
ha
ng
e
a
n
d
c
o
ope
r
a
t
io
n
[
3
]
.
C
lo
ud
-
ba
s
e
d
s
ys
tem
s
ma
y
b
u
il
d
c
om
pl
e
x
c
on
t
in
uo
us
E
E
G
a
na
lys
is
a
lg
o
r
i
th
ms
due
to
t
he
ir
hi
gh
p
r
o
c
e
s
s
in
g
c
a
pa
bi
li
t
ies
.
C
lo
ud
r
e
s
ou
r
c
e
s
a
r
e
s
c
a
l
a
b
le
s
o
the
s
ys
t
e
m
c
a
n
h
a
n
dl
e
a
r
is
i
ng
mo
un
ta
in
of
da
ta
f
o
r
r
e
a
l
-
t
im
e
mo
ni
t
or
i
ng
a
nd
a
na
l
ys
is
.
T
h
is
s
t
ud
y
c
om
b
ines
c
lo
ud
c
om
pu
t
in
g
in
f
r
a
s
t
r
u
c
t
ur
e
s
to
s
w
if
t
l
y
in
te
r
pr
e
t
E
E
G
da
ta
f
o
r
e
pi
le
pt
ic
s
e
izu
r
e
a
na
ly
s
is
a
nd
p
r
e
d
ic
ti
on
[
4]
.
C
l
ou
d
c
o
mp
ut
i
ng
a
nd
po
we
r
f
u
l
im
a
g
i
ng
a
nd
s
ig
na
l
p
r
o
c
e
s
s
in
g
m
a
y
h
e
l
p
p
r
e
d
ic
t
e
pi
le
pt
ic
s
e
iz
u
r
e
s
.
I
ma
ge
pr
oc
e
s
s
i
ng
may
r
e
ve
a
l
b
r
a
in
a
c
t
iv
i
ty
a
no
ma
li
e
s
t
ha
t
p
r
e
c
e
de
s
e
iz
u
r
e
s
i
n
E
E
G
i
ma
ge
s
[
5
]
.
C
on
te
mp
o
r
a
r
y
w
a
ve
le
t
t
r
a
ns
f
o
r
ms
a
n
d
ne
u
r
a
l
ne
two
r
k
me
t
ho
ds
e
xa
m
ine
E
E
G
da
ta
i
n
t
he
f
r
e
q
ue
n
c
y
do
ma
i
n
to
d
e
t
e
c
t
m
in
ut
e
s
e
iz
ur
e
s
i
gn
a
ls
.
T
his
p
r
o
je
c
t
wi
ll
c
om
b
in
e
ma
ny
me
th
od
o
lo
gi
e
s
i
nt
o
a
pr
e
d
ic
ti
ve
mo
de
l
t
ha
t
c
a
n
r
e
c
og
n
ize
c
om
p
lex
pa
tt
e
r
ns
a
nd
o
ut
l
ie
r
s
t
o
e
n
ha
nc
e
s
e
iz
ur
e
p
r
e
di
c
t
io
ns
.
C
l
ou
d
c
om
pu
ti
ng
in
f
r
a
s
t
r
u
c
t
u
r
e
f
o
r
f
a
s
t
a
na
lys
is
a
nd
r
e
a
l
-
t
i
me
p
r
e
d
ict
i
on
im
pr
ov
e
s
e
p
i
le
ps
y
ma
na
ge
m
e
n
t
e
f
f
i
c
i
e
nc
y
[
6
]
.
T
h
is
r
e
s
e
a
r
c
h
e
xa
mi
n
e
s
h
ow
c
lo
ud
c
o
mp
ut
in
g
,
i
ma
ge
p
r
oc
e
s
s
in
g
,
a
nd
s
i
gn
a
l
p
r
oc
e
s
s
in
g
m
a
y
a
nt
ic
ip
a
t
e
e
p
il
e
p
ti
c
s
e
izu
r
e
s
.
A
r
e
l
iab
le
p
r
e
d
ic
ti
on
m
od
e
l
t
ha
t
c
a
n
gr
e
a
tl
y
e
n
ha
n
c
e
e
p
il
e
ps
y
p
a
t
ie
nts
'
a
c
c
e
s
s
to
p
e
r
s
o
na
li
z
e
d
t
he
r
a
py
i
s
the
ma
in
a
i
m
.
T
h
is
s
tu
dy
a
i
ms
to
c
r
e
a
te
a
nd
de
p
lo
y
a
c
lo
ud
-
ba
s
e
d
p
la
t
f
o
r
m
t
ha
t
p
r
oc
e
s
s
e
s
mas
s
i
ve
E
E
G
d
a
t
a
s
e
t
s
us
in
g
c
u
tt
i
n
g
-
e
d
ge
i
m
a
ge
a
n
d
s
i
gn
a
l
p
r
oc
e
s
s
i
ng
a
l
go
r
it
hm
s
t
o
i
de
nt
i
f
y
e
a
r
ly
e
p
il
e
p
ti
c
e
p
is
ode
s
[
7
]
.
T
h
e
c
on
ve
r
ge
nc
e
o
f
c
ut
ti
ng
-
e
d
ge
t
e
c
hn
ol
og
y
ha
s
tr
a
ns
f
o
r
med
he
a
l
thc
a
r
e
b
y
s
o
lv
in
g
in
no
va
t
i
ve
n
e
w
i
s
s
u
e
s
.
U
np
r
e
d
ict
a
b
il
i
ty
ma
ke
s
e
p
i
le
ps
y
on
e
of
n
um
e
r
o
us
he
a
lt
h
dis
o
r
d
e
r
s
d
i
f
f
i
c
u
lt
.
D
ue
to
t
he
ne
c
e
s
s
it
y
f
or
t
i
me
ly
a
c
ti
on
,
e
p
i
lep
t
ic
s
e
iz
u
r
e
p
r
e
d
ic
ti
on
us
e
s
c
lou
d
c
o
mp
ut
in
g
,
im
a
ge
p
r
o
c
e
s
s
in
g
,
a
nd
s
i
gna
l
p
r
oc
e
s
s
in
g
[
8
]
.
C
lo
ud
c
o
m
pu
ti
ng
,
a
tec
hn
ic
a
l
ma
r
ve
l
th
a
t
ha
s
s
m
a
s
h
e
d
b
or
de
r
s
,
u
nde
r
pi
ns
th
is
ne
w
c
onc
e
p
t
.
C
lo
ud
c
om
p
ut
ing
h
a
s
a
lt
e
r
e
d
h
e
a
lt
hc
a
r
e
wi
th
it
s
s
c
a
l
a
b
le
,
o
n
-
d
e
m
a
nd
in
f
r
a
s
t
r
u
c
t
u
r
e
a
nd
i
n
f
o
r
ma
ti
on
e
xc
ha
n
ge
c
a
p
a
b
il
it
i
e
s
.
T
he
c
lo
ud
c
a
n
s
e
c
u
r
e
l
y
s
t
or
e
h
uge
E
E
G
da
ta
f
o
r
e
pi
lep
s
y
m
a
n
a
ge
me
nt
.
T
he
c
lo
ud
's
f
le
x
ib
il
it
y
m
e
e
ts
p
r
o
c
e
s
s
in
g
d
e
m
a
n
ds
,
e
na
bl
in
g
c
om
pl
e
x
r
e
a
l
-
t
im
e
E
E
G
a
na
lys
is
m
e
t
ho
ds
[
9
]
.
I
nn
ov
a
t
iv
e
i
ma
ge
a
n
d
s
i
gn
a
l
p
r
o
c
e
s
s
in
g
a
pp
r
oa
c
he
s
ha
ve
be
e
n
c
r
e
a
t
e
d
a
l
on
gs
ide
t
he
c
l
ou
d's
c
a
p
a
b
il
i
ti
e
s
.
R
e
s
e
a
r
c
he
r
s
ha
v
e
u
nd
e
r
s
t
oo
d
c
om
ple
x
E
E
G
s
pa
t
ia
l
pa
t
te
r
ns
u
s
i
ng
a
dva
nc
e
d
i
ma
ge
p
r
o
c
e
s
s
in
g
.
E
E
G
r
e
c
o
r
d
in
gs
ma
y
be
a
na
ly
z
e
d
us
i
ng
F
ou
r
ie
r
a
na
lys
is
a
nd
m
a
c
hi
ne
lea
r
ni
ng
tec
hn
iq
ue
s
to
id
e
n
ti
f
y
te
m
po
r
a
l
a
n
d
s
p
e
c
t
r
a
l
c
ha
ng
e
s
t
ha
t
ma
y
s
u
gg
e
s
t
a
s
e
i
z
u
r
e
.
Us
in
g
t
he
s
e
s
t
r
a
t
e
g
ies
e
nh
a
n
c
e
s
p
r
e
d
ic
ti
on
mo
de
l
r
e
s
il
ie
nc
e
a
n
d
a
c
c
u
r
a
c
y
[
10
]
.
T
h
is
n
ov
e
l
a
pp
r
oa
c
h
t
o
e
x
pa
nd
in
g
he
a
l
th
c
a
r
e
t
e
c
h
no
l
og
y
us
a
ge
is
a
n
e
s
s
e
n
ti
a
l
a
dd
it
io
n
t
o
t
he
a
r
e
a
.
T
he
s
tu
dy
me
th
od
o
lo
gy
's
e
mp
ha
s
is
o
n
p
r
e
d
ic
t
ive
a
lg
or
i
t
hms
a
n
d
a
n
a
p
pe
a
li
ng
us
e
r
i
nt
e
r
f
a
c
e
e
ns
u
r
e
s
a
c
c
e
s
s
i
bi
li
ty
a
nd
us
e
r
-
f
r
ie
nd
li
ne
s
s
f
o
r
he
a
l
th
c
a
r
e
p
r
o
f
e
s
s
i
on
a
ls
a
nd
p
a
t
ie
nts
[
1
1
]
.
E
pi
le
ps
y
's
nu
me
r
o
us
b
r
a
in
a
bn
or
m
a
l
i
ti
e
s
h
a
v
e
l
on
g
be
e
n
d
i
f
f
i
c
u
lt
to
t
r
e
a
t
.
De
c
i
ph
e
r
in
g
s
e
iz
u
r
e
p
a
t
te
r
ns
r
e
qu
i
r
e
s
un
iq
ue
m
e
t
ho
do
lo
g
ies
du
e
t
o
i
ts
u
n
pr
e
d
ic
tab
i
li
ty
.
E
E
G
r
e
a
l
-
ti
me
b
r
a
in
a
c
ti
v
it
y
a
na
lys
is
is
a
hu
ge
s
te
p
to
wa
r
d
a
c
c
u
r
a
te
ly
p
r
e
di
c
t
in
g
a
nd
t
r
e
a
t
in
g
s
e
iz
u
r
e
s
[
1
2
]
.
He
a
l
th
c
a
r
e
i
s
bo
o
mi
ng
,
a
nd
c
l
ou
d
c
om
p
ut
in
g
is
ke
y
.
B
e
c
a
us
e
i
t
c
a
n
by
pa
s
s
ph
ys
i
c
a
l
c
o
ns
t
r
a
i
n
ts
,
i
t
h
a
s
e
nd
les
s
s
to
r
a
ge
a
n
d
p
r
o
c
e
s
s
in
g
p
owe
r
,
o
f
f
e
r
i
ng
n
e
w
me
dic
a
l
r
e
s
e
a
r
c
h
o
pt
i
ons
.
T
he
c
lo
ud
c
a
n
i
mm
e
d
ia
te
ly
h
a
n
dl
e
e
n
o
r
m
ous
E
E
G
d
a
ta
f
o
r
e
pi
le
ps
y
r
e
s
e
a
r
c
h
a
s
a
v
i
r
tua
l
ne
u
r
a
l
ne
tw
or
k
[
13
]
.
O
nl
y
c
o
nt
e
m
po
r
a
r
y
im
a
ge
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
lec
&
C
omp
E
ng
I
S
S
N:
2088
-
8708
C
loud
bas
e
d
pr
e
diction
of
e
pil
e
pti
c
s
e
iz
ur
e
s
us
ing
r
e
al
-
ti
me
e
lec
tr
oe
nc
e
phalogr
am
s
…
(
Gous
ia
T
hah
niyath
)
6049
a
nd
s
ig
na
l
p
r
o
c
e
s
s
in
g
a
p
p
r
oa
c
h
e
s
ma
y
r
e
v
e
a
l
c
r
uc
ia
l
i
ns
i
gh
ts
i
n
to
E
E
G
d
a
t
a
.
I
ma
ge
p
r
oc
e
s
s
i
ng
t
e
c
hn
iq
ue
s
m
e
ti
c
u
lo
us
l
y
a
n
a
l
yz
e
E
E
G
i
mag
e
s
t
o
r
e
v
e
a
l
un
de
te
c
t
a
b
le
p
a
t
te
r
n
s
.
Ad
va
nc
e
d
te
m
po
r
a
l
a
n
d
f
r
e
q
ue
nc
y
do
ma
in
s
ig
na
l
p
r
oc
e
s
s
i
ng
ma
y
de
tec
t
s
e
iz
u
r
e
p
r
e
c
u
r
s
o
r
s
[
14]
.
I
t
i
s
e
a
s
i
e
r
t
o
de
a
l
wi
th
d
e
ta
i
ls
a
nd
a
s
s
e
ts
c
r
e
a
ti
ng
a
m
or
e
c
oh
e
s
i
ve
e
c
os
ys
t
e
m
[
1
5
]
.
I
nc
r
e
a
s
e
d
c
o
nne
c
t
iv
i
ty
a
n
d
p
r
o
du
c
t
iv
i
ty
i
n
t
he
c
lo
ud
a
r
e
b
ot
h
be
n
e
f
i
ts
o
f
i
n
te
r
o
pe
r
a
bi
l
it
y
.
I
t
e
x
pa
nds
o
u
r
kn
ow
led
ge
o
f
e
pi
lep
s
y
a
n
d
f
o
r
e
s
ha
d
ows
a
h
um
a
n
e
me
di
c
a
l
tec
hn
ol
ogy
.
C
lo
ud
c
om
pu
t
in
g
,
i
ma
ge
p
r
oc
e
s
s
in
g
,
a
nd
s
ig
na
l
p
r
o
c
e
s
s
in
g
e
na
ble
us
t
o
u
nd
e
r
s
ta
nd
s
e
i
z
u
r
e
s
a
t
a
ba
s
ic
l
e
v
e
l
r
a
th
e
r
t
ha
n
m
e
r
e
ly
p
r
e
di
c
t
t
he
m
.
T
h
e
r
e
s
ul
ts
o
f
th
is
in
ve
s
ti
ga
ti
on
a
r
e
s
i
gn
i
f
i
c
a
n
t
f
o
r
c
r
e
a
t
in
g
pe
r
s
o
na
li
z
e
d
e
pi
le
ps
y
tr
e
a
t
men
t
p
r
og
r
a
ms
[
16
]
.
T
he
da
ta
is
s
to
r
e
d
,
a
na
ly
z
e
d
,
a
nd
s
ho
wn
us
in
g
T
h
i
ng
S
p
e
a
k
,
a
c
l
ou
d
-
ba
s
e
d
I
o
T
p
la
t
f
o
r
m.
I
t
h
a
s
a
s
im
pl
e
i
nt
e
r
f
a
c
e
w
h
ich
c
a
n
be
u
t
il
iz
e
d
to
o
bs
e
r
v
e
wa
te
r
lev
e
ls
,
obs
e
r
ve
da
ta
f
r
o
m
t
he
p
a
s
t
,
a
nd
e
x
pa
n
d
d
is
c
ov
e
r
i
ng
wh
ic
h
c
a
n
be
a
p
pl
ie
d
t
o
h
a
n
dl
e
wa
te
r
r
e
s
ou
r
c
e
s
be
t
te
r
[
1
7]
.
E
p
i
lep
t
ic
s
e
izu
r
e
s
,
wh
ich
c
a
us
e
s
ud
de
n
,
a
bn
o
r
m
a
l
br
a
in
e
lec
t
r
i
c
a
l
a
c
t
i
vi
ty
,
p
r
e
s
e
n
t
s
e
v
e
r
a
l
pr
ob
le
ms
t
o
n
e
u
r
ol
og
y
.
De
s
p
it
e
a
d
va
nc
e
s
,
do
c
t
or
s
a
i
m
to
pr
e
d
ic
t
t
he
s
e
s
e
izu
r
e
s
.
C
l
ou
d
c
om
pu
ti
ng
,
i
mag
e
p
r
oc
e
s
s
i
n
g
,
a
n
d
s
ig
na
l
p
r
oc
e
s
s
i
ng
ma
y
he
lp
s
ol
ve
c
om
pl
e
x
b
r
a
i
n
s
i
g
na
ls
in
th
e
di
g
it
a
l
a
ge
[
18
]
.
S
c
a
la
bl
e
a
n
d
a
v
a
i
la
bl
e
c
lo
ud
t
e
c
hn
ol
og
ies
a
r
e
th
e
di
g
it
a
l
c
a
nv
a
s
f
o
r
th
is
i
nn
ov
a
ti
ve
un
de
r
t
a
k
in
g
.
C
l
ou
d
c
o
mp
u
ti
ng
a
c
ts
a
s
a
"
v
i
r
tua
l
ne
u
r
a
l
n
e
t
wo
r
k
.
"
in
e
p
i
lep
s
y
r
e
s
e
a
r
c
h
p
r
oc
e
s
s
i
ng
,
h
a
v
in
g
m
a
s
s
iv
e
a
m
ou
nts
o
f
in
f
o
r
m
a
t
io
n
in
r
e
a
l
-
t
im
e
.
T
he
c
lo
ud
'
s
c
ol
la
bo
r
a
t
iv
e
c
a
p
a
b
il
i
ti
e
s
a
l
lo
w
r
e
s
e
a
r
c
he
r
s
to
e
xa
mi
ne
u
nd
is
c
ov
e
r
e
d
E
E
G
da
ta
,
e
nc
o
u
r
a
gi
ng
a
gl
ob
a
l
i
n
f
o
r
ma
ti
on
-
s
ha
r
in
g
ne
tw
o
r
k
[
1
9
]
.
Ac
c
u
r
a
te
s
e
iz
u
r
e
p
r
e
d
ic
ti
on
r
e
qu
i
r
e
s
i
ma
gi
ng
a
n
d
s
i
gna
l
p
r
oc
e
s
s
i
ng
.
I
ns
p
ir
e
d
b
y
n
e
u
r
a
l
n
e
t
wo
r
ks
,
im
a
g
e
p
r
o
c
e
s
s
in
g
me
th
ods
de
c
ip
he
r
c
om
p
li
c
a
t
e
d
s
pa
t
ia
l
p
a
t
te
r
n
s
in
E
E
G
i
mag
e
s
t
o
c
a
p
tu
r
e
d
e
t
a
i
ls
t
he
h
um
a
n
e
ye
m
is
s
e
s
.
S
i
gna
l
p
r
o
c
e
s
s
in
g
s
ys
t
e
ms
mus
t
c
r
os
s
the
f
r
e
que
nc
y
s
pe
c
t
r
u
m
t
o
un
de
r
s
tan
d
E
E
G
t
e
mp
or
a
l
d
e
t
a
i
ls
.
C
o
mb
in
in
g
th
e
s
e
s
t
r
a
te
gi
e
s
is
l
ik
e
a
j
i
gs
a
w
p
uz
z
le
w
i
th
c
o
nn
e
c
ted
p
ie
c
e
s
[
20
]
.
I
t
s
i
gn
a
l
s
a
ne
w
e
r
a
in
n
e
u
r
o
l
og
ica
l
c
a
r
e
,
w
he
r
e
d
a
ta
-
d
r
i
ve
n
ins
ig
h
ts
w
il
l
r
e
de
f
in
e
pa
ti
e
n
t
e
x
pe
r
i
e
nc
e
.
T
his
r
e
s
e
a
r
c
h
im
a
g
i
ne
s
a
f
u
tu
r
e
w
he
r
e
e
pi
le
ps
y
pa
ti
e
n
ts
m
a
y
us
e
tec
hn
ol
og
ic
a
l
l
y
a
dva
nc
e
d
s
o
c
i
a
l
ne
tw
or
ks
f
o
r
c
o
m
f
o
r
t
a
n
d
s
u
pp
or
t
[
21
]
.
E
p
i
lep
t
ic
s
e
iz
ur
e
s
te
s
t
the
br
a
i
n's
de
li
c
a
t
e
ne
u
r
o
na
l
d
a
nc
e
m
ys
te
r
io
us
ly
.
D
e
s
p
it
e
me
di
c
a
l
a
d
va
nc
e
s
,
e
pi
le
pt
ic
s
e
iz
ur
e
pr
e
d
ic
ti
on
r
e
mai
ns
di
f
f
ic
ul
t
.
C
lo
u
d
c
om
pu
t
in
g
,
im
a
ge
p
r
oc
e
s
s
in
g
,
a
n
d
s
ig
na
l
p
r
o
c
e
s
s
in
g
i
l
lu
m
ina
te
br
a
i
nw
a
ve
s
in
th
e
d
ig
it
a
l
a
ge
[
2
2
]
.
C
l
ou
d
c
om
pu
ti
ng
is
a
n
e
x
a
m
pl
e
o
f
h
um
a
n
c
r
e
a
t
i
vi
ty
in
the
di
gi
ta
l
c
os
m
os
,
p
r
ov
id
in
g
a
n
a
l
mos
t
e
nd
les
s
c
a
n
va
s
f
o
r
c
om
pu
ta
t
io
na
l
r
e
s
e
a
r
c
h
.
C
l
ou
d
s
ys
te
ms
d
r
ive
ne
ur
o
s
c
i
e
n
c
e
b
r
e
a
k
t
hr
ou
ghs
be
c
a
us
e
o
f
th
e
i
r
s
c
a
l
a
b
il
i
ty
a
n
d
c
o
mp
u
ta
ti
ona
l
po
we
r
.
I
n
e
p
il
e
ps
y
r
e
s
e
a
r
c
h
,
the
c
l
ou
d
be
c
o
mes
a
b
r
a
i
n
ne
xus
whe
r
e
po
we
r
f
u
l
a
l
go
r
i
th
ms
c
a
n
i
mm
e
d
ia
te
ly
a
na
ly
z
e
m
a
s
s
i
ve
da
t
a
.
C
l
ou
d
-
ba
s
e
d
to
ols
s
p
e
e
d
up
r
e
s
e
a
r
c
h
a
n
d
e
n
a
b
le
s
c
ie
nt
is
t
s
to
s
tu
dy
E
E
G
da
ta
[
2
3
]
de
e
p
ly
.
A
de
ta
il
e
d
u
nd
e
r
s
ta
nd
i
ng
o
f
br
a
i
n
s
i
g
na
ls
is
n
e
e
de
d
to
a
n
ti
c
i
pa
te
e
pi
le
ps
y
a
c
c
ur
a
t
e
l
y
.
I
ns
p
i
r
e
d
by
th
e
b
r
a
in
's
n
e
u
r
a
l
n
e
t
wo
r
k
s
,
i
mag
e
p
r
o
c
e
s
s
in
g
t
e
c
h
n
iq
ue
s
e
xa
mi
ne
E
E
G
im
a
g
e
s
p
ixe
l
b
y
p
ix
e
l
to
id
e
n
ti
f
y
t
iny
c
h
a
n
ge
s
.
S
i
gna
l
p
r
oc
e
s
s
i
ng
met
ho
ds
c
onc
u
r
r
e
n
t
ly
e
xp
lo
r
e
t
he
t
im
e
a
nd
f
r
e
qu
e
n
c
y
do
ma
ins
t
o
u
nd
e
r
s
ta
nd
br
a
in
wa
v
e
d
yn
a
m
ics
[
24
]
.
T
h
is
w
o
r
k
il
l
um
in
a
te
s
a
ga
me
-
c
ha
ng
in
g
po
te
nt
ia
l
f
o
r
ne
u
r
o
lo
gi
c
a
l
th
e
r
a
p
y
be
yo
nd
f
un
da
me
nt
a
l
s
c
ie
nc
e
.
W
he
n
ph
ys
i
c
i
a
ns
c
a
n
p
r
e
di
c
t
s
e
izu
r
e
s
i
n
r
e
a
l
-
ti
me
,
e
pi
le
p
ti
c
pa
ti
e
n
ts
m
a
y
f
e
e
l
mo
r
e
i
n
c
o
n
tr
o
l
a
n
d
c
on
f
ide
nt
.
C
o
mb
in
in
g
c
lo
ud
c
o
mp
ut
in
g,
i
ma
ge
p
r
oc
e
s
s
i
ng
,
a
nd
s
i
gn
a
l
p
r
oc
e
s
s
in
g
us
he
r
s
in
p
a
t
ie
nt
-
c
e
n
te
r
e
d
,
c
o
mp
a
s
s
i
on
a
t
e
he
a
l
thc
a
r
e
[
25
]
.
T
he
i
r
u
n
pr
e
d
ic
tab
i
li
ty
c
ha
l
len
ge
s
me
di
c
a
l
e
x
pe
r
ti
s
e
,
s
p
a
r
k
in
g
a
q
ue
s
t
f
o
r
n
e
w
t
r
e
a
tm
e
n
ts
.
C
o
mb
i
ni
ng
c
l
ou
d
c
om
pu
t
in
g
,
i
mag
e
,
a
n
d
s
ig
na
l
p
r
o
c
e
s
s
in
g
t
r
a
ns
f
o
r
ms
e
pi
le
pt
ic
b
r
a
i
nwa
ve
u
nde
r
s
ta
nd
in
g
[
26
]
.
C
lo
ud
c
om
p
ut
in
g
h
a
s
r
e
v
o
lu
ti
on
ize
d
n
e
u
r
a
l
d
a
t
a
a
n
a
l
ys
is
.
C
l
ou
d
s
e
r
vi
c
e
s
m
a
y
be
c
om
e
ne
u
r
a
l
ne
tw
o
r
ks
wi
th
e
x
t
r
a
o
r
di
na
r
y
p
r
oc
e
s
s
i
ng
po
we
r
in
t
his
e
no
r
mo
us
c
yb
e
r
s
pa
c
e
.
C
lou
d
c
o
mp
ut
in
g
gi
ve
s
r
e
s
e
a
r
c
he
r
s
a
c
c
e
s
s
to
u
nd
is
c
o
ve
r
e
d
E
E
G
d
a
t
a
.
I
ts
s
c
a
la
b
il
it
y
a
ll
ows
s
ys
t
e
m
a
t
ic
a
na
lys
is
o
f
e
pi
l
e
p
ti
c
b
r
a
in
a
c
t
iv
i
ty
,
lea
di
ng
to
une
xp
e
c
ted
r
e
s
u
lt
s
[
2
7
]
.
T
he
s
c
op
e
is
t
o
e
x
pa
n
d
a
n
I
o
T
s
ys
te
m
t
ha
t
a
s
s
is
ts
s
u
s
ta
i
na
b
i
li
ty
a
nd
e
ne
r
g
y
e
f
f
ic
ie
nc
y
by
p
r
ov
id
in
g
r
e
a
l
-
ti
me
o
bs
e
r
va
ti
on
a
n
d
ins
ig
hts
i
nt
o
po
we
r
ut
il
iz
a
t
io
n
[
2
8]
.
T
h
e
be
n
e
f
i
ts
o
f
i
nc
o
r
p
or
a
t
in
g
th
e
I
n
te
r
ne
t
o
f
T
hi
n
gs
a
nd
G
e
o
g
r
a
p
hi
c
I
nf
o
r
m
a
t
io
n
S
ys
t
e
ms
i
n
a
g
r
icu
l
tu
r
e
,
w
it
h
a
pa
r
ti
c
u
la
r
a
c
c
e
n
t
on
t
he
p
os
s
i
bi
l
it
y
o
f
t
r
a
ns
f
o
r
m
i
ng
s
o
il
o
bs
e
r
vi
ng
a
n
d
n
ut
r
ien
t
ma
na
g
e
m
e
n
t
t
o
r
a
is
e
c
r
op
out
p
ut
wh
il
e
m
in
i
mi
z
i
ng
ne
g
a
t
iv
e
e
nv
i
r
o
nme
n
tal
e
f
f
e
c
t
s
[
2
9]
.
2.
M
E
T
HO
D
T
he
n
o
ta
t
io
n
d
e
picts
a
c
onve
nti
ona
l
10
-
20
E
E
G
e
lec
tr
ode
plac
e
ment
method.
T
his
br
a
in
a
c
ti
vit
y
mapping
tec
hnique
is
uti
li
z
e
d
c
li
nica
ll
y
.
Odd
-
num
be
r
e
d
e
lec
tr
ode
s
a
r
e
plac
e
d
on
the
lef
t
s
ide
o
f
the
s
c
a
lp,
a
nd
e
ve
n
-
number
e
d
e
lec
tr
ode
s
on
the
r
ight
.
E
pil
e
ps
y
diagnos
is
a
nd
tr
e
a
tm
e
nt
typi
c
a
ll
y
include
E
E
G
m
onit
or
ing.
C
e
r
tain
br
a
in
e
lec
tr
ica
l
a
c
ti
vit
y
pa
tt
e
r
ns
may
s
ignal
e
pil
e
ps
y
or
a
s
s
is
t
in
diagnos
ing
it
on
the
E
E
G.
2.
1.
Dif
f
e
r
e
n
t
t
yp
e
s
of
E
E
G
2.
1.
1.
Rout
in
e
E
E
G
T
his
is
the
s
tanda
r
d
E
E
G
r
e
c
or
ding
typi
c
a
ll
y
done
in
a
c
li
nica
l
s
e
tt
ing.
I
t
invol
ve
s
plac
ing
e
lec
tr
ode
s
on
the
s
c
a
lp
to
r
e
c
or
d
e
lec
tr
ica
l
a
c
ti
vit
y
f
r
om
th
e
br
a
in,
us
ua
ll
y
20
-
30
mi
nutes
.
R
outi
ne
E
E
G
c
a
n
c
a
ptur
e
int
e
r
icta
l
e
pil
e
pti
f
or
m
dis
c
ha
r
ge
s
,
whic
h
a
r
e
a
bnor
mal
e
lec
tr
ica
l
pa
tt
e
r
ns
be
twe
e
n
s
e
izur
e
s
,
a
nd
he
lp
in
diagnos
ing
e
pil
e
ps
y.
P
r
os
:
R
outi
ne
E
E
G
is
non
-
invas
ive,
r
e
latively
inexpe
ns
ive,
a
nd
r
e
a
dil
y
a
va
i
lable
.
I
t
he
lps
in
diagnos
ing
e
pil
e
ps
y
by
de
tec
ti
ng
int
e
r
ict
a
l
e
pil
e
pti
f
or
m
dis
c
ha
r
ge
s
.
I
t
c
a
n
a
ls
o
p
r
ovide
inf
or
mation
a
bout
ba
c
kgr
ound
br
a
in
a
c
ti
vit
y
a
nd
a
s
s
is
t
in
mon
it
or
ing
the
e
f
f
e
c
ts
of
medic
a
ti
on.
C
ons
:
R
outi
ne
E
E
G
ha
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
1
4
,
No.
5
,
Oc
tober
2
02
4
:
6047
-
6056
6050
li
mi
tations
in
c
a
ptur
ing
e
pil
e
pti
c
e
ve
nts
,
a
s
it
o
nly
r
e
c
or
ds
f
o
r
a
s
hor
t
du
r
a
ti
on
a
nd
may
mi
s
s
tr
a
ns
ient
a
bnor
malit
ies
.
I
t
may
not
a
lwa
ys
c
or
r
e
late
with
c
li
nica
l
s
ympt
oms
,
lea
ding
to
f
a
ls
e
-
ne
ga
ti
ve
or
f
a
ls
e
-
pos
it
ive
r
e
s
ult
s
.
I
nter
pr
e
tation
of
r
outi
ne
E
E
G
r
e
qui
r
e
s
e
xpe
r
ti
s
e
,
a
nd
s
ubtl
e
a
bnor
malit
ies
c
a
n
be
ove
r
looked.
F
igur
e
1
s
hows
the
hybr
id
mac
hine
lea
r
ning
-
s
wa
r
m
int
e
ll
igenc
e
e
pil
e
pti
c
s
e
izur
e
de
tec
ti
on
model.
Huma
n
br
a
in
E
E
G
da
ta
a
r
e
pr
e
pr
oc
e
s
s
e
d
a
nd
us
e
d
f
o
r
s
tati
ona
r
y
wa
ve
let
t
r
a
ns
f
or
mation.
E
E
G
wa
ve
s
a
r
e
divi
de
d
int
o
many
s
ubba
nds
.
T
he
mea
n
a
bs
olut
e
va
lue,
s
tanda
r
d
de
viation,
s
ke
wne
s
s
,
kur
tos
is
,
r
oot
mea
n
s
qua
r
e
(
R
M
S
)
powe
r
,
the
r
a
ti
o
o
f
ne
ighbor
ing
s
ub
-
ba
nds
mea
n
a
bs
olut
e
va
lues
,
a
nd
other
Hjor
th
pa
r
a
mete
r
s
ha
ve
be
e
n
r
e
tr
ieve
d
a
s
f
e
a
tur
e
s
f
or
e
a
c
h
c
oe
f
f
icie
nt
in
e
a
c
h
s
ub
-
ba
nd.
T
he
de
e
p
ne
u
r
a
l
ne
twor
k
(
DN
N)
model
i
s
tr
a
ined
us
ing
opti
mum
f
e
a
tur
e
s
picke
d
us
ing
the
binar
y
d
r
a
gonf
ly
method
f
r
om
e
a
c
h
s
ub
-
br
a
nds
r
e
tr
ieve
d
f
e
a
tur
e
s
.
Af
ter
tr
a
ini
ng
,
the
model
c
las
s
if
ied
E
E
G
s
ignals
a
s
s
e
izur
e
or
no
r
mal.
F
igur
e
1.
S
ys
tem
f
low
diagr
a
m
f
or
e
pil
e
pti
c
s
e
izur
e
de
tec
ti
on
2.
1.
2.
L
on
g
-
t
e
r
m
v
id
e
o
E
E
G
m
on
i
t
or
in
g
L
T
M
invol
ve
s
c
onti
nuous
E
E
G
r
e
c
or
ding
c
ombi
ne
d
with
s
im
ult
a
ne
ous
video
moni
to
r
ing
ove
r
a
n
e
xtende
d
pe
r
iod,
r
a
nging
f
r
om
s
e
ve
r
a
l
hour
s
to
da
ys
or
we
e
ks
.
T
his
type
of
E
E
G
is
c
r
uc
ial
f
or
c
a
ptur
ing
s
e
izur
e
e
ve
nts
a
nd
c
or
r
e
lating
them
with
E
E
G
f
i
ndings
.
I
t
p
r
ovides
va
luable
inf
or
mation
f
or
de
te
r
mi
ning
s
e
izur
e
type,
loca
li
z
a
ti
on,
f
r
e
que
nc
y,
a
nd
r
e
s
pons
e
to
tr
e
a
tm
e
nt.
P
r
os
:
L
T
M
a
ll
ows
c
onti
nuous
r
e
c
or
ding
of
E
E
G
a
c
ti
vi
ty
a
nd
video
moni
to
r
ing,
e
na
bli
ng
the
c
or
r
e
lation
o
f
c
li
nica
l
e
ve
nts
with
E
E
G
f
indi
ngs
.
I
t
pr
ovides
c
ompr
e
he
ns
ive
da
ta
on
s
e
izur
e
f
r
e
que
nc
y,
du
r
a
ti
o
n,
a
nd
s
e
mi
ology,
a
idi
ng
diagnos
is
a
nd
t
r
e
a
tm
e
nt
planning.
L
T
M
c
a
n
c
a
ptur
e
both
icta
l
a
nd
int
e
r
icta
l
e
pil
e
pti
f
or
m
dis
c
ha
r
ge
s
,
e
nha
nc
ing
diagnos
ti
c
yield.
C
ons
:
L
T
M
is
r
e
s
our
c
e
-
int
e
ns
iv
e
,
r
e
quir
ing
s
pe
c
ialize
d
e
quipm
e
nt
a
nd
pe
r
s
onne
l
f
or
pr
olonged
moni
tor
ing
.
P
a
ti
e
nt
c
ompl
ianc
e
a
nd
tol
e
r
a
nc
e
f
or
long
-
ter
m
moni
tor
in
g
may
pos
e
c
ha
ll
e
nge
s
.
I
nter
pr
e
tation
of
L
T
M
r
e
c
or
dings
c
a
n
be
ti
me
-
c
ons
umi
ng
a
nd
may
r
e
quir
e
e
xpe
r
t
r
e
view
.
E
E
G
s
ignals
a
r
e
r
e
c
or
de
d
to
identif
y
e
pil
e
pti
c
s
e
izur
e
s
.
P
r
e
-
pr
oc
e
s
s
ing
include
s
s
a
mpl
ing,
f
il
ter
i
ng,
a
nd
a
r
ti
f
a
c
t
r
e
moval.
A
f
ter
p
r
e
-
pr
oc
e
s
s
ing,
the
s
ignal
is
f
e
a
tur
e
e
xtr
a
c
ted
f
or
c
a
tegor
iza
ti
on.
F
inal
c
a
te
gor
iza
ti
on
us
e
s
mac
hine
-
lea
r
ning
a
ppr
oa
c
he
s
to
identif
y
e
pil
e
ps
y.
F
igur
e
2
de
picts
the
pr
oc
e
dur
e
.
F
igur
e
2.
De
tec
ti
ng
e
pil
e
ps
y
s
e
izur
e
s
2.
1.
3.
Am
b
u
lat
or
y
E
E
G
Ambulator
y
E
E
G
invol
ve
s
r
e
c
or
ding
E
E
G
a
c
ti
vit
y
while
the
pa
ti
e
nt
e
nga
ge
s
in
nor
mal
da
il
y
a
c
ti
vit
ies
outs
ide
the
hos
pit
a
l
s
e
tt
ing.
T
he
e
lec
t
r
ode
s
a
r
e
us
ua
ll
y
a
tt
a
c
he
d
to
the
s
c
a
lp
with
a
por
table
r
e
c
or
ding
de
vice
wor
n
by
the
pa
ti
e
nt
.
Ambulator
y
E
E
G
c
a
n
pr
ovide
ins
ight
s
in
to
s
e
izur
e
pa
tt
e
r
ns
that
may
not
be
c
a
ptur
e
d
dur
ing
r
outi
ne
E
E
G
a
nd
c
a
n
a
ls
o
h
e
lp
a
s
s
e
s
s
the
e
f
f
ica
c
y
of
medic
a
ti
ons
a
nd
identi
f
y
tr
igger
s
f
or
s
e
izur
e
s
.
P
r
os
:
Ambulator
y
E
E
G
a
ll
ows
r
e
c
or
ding
br
a
in
a
c
ti
vit
y
ove
r
a
n
e
xtende
d
pe
r
iod
in
the
pa
ti
e
nt's
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
lec
&
C
omp
E
ng
I
S
S
N:
2088
-
8708
C
loud
bas
e
d
pr
e
diction
of
e
pil
e
pti
c
s
e
iz
ur
e
s
us
ing
r
e
al
-
ti
me
e
lec
tr
oe
nc
e
phalogr
am
s
…
(
Gous
ia
T
hah
niyath
)
6051
na
tur
a
l
e
nvir
onment,
incr
e
a
s
ing
the
li
ke
li
hood
of
c
a
ptur
ing
s
e
izur
e
e
ve
nts
that
may
not
oc
c
ur
dur
ing
a
r
outi
ne
E
E
G.
I
t
pr
ovides
va
luable
ins
ight
s
int
o
da
il
y
pa
t
ter
ns
of
s
e
izur
e
a
c
ti
vit
y
a
nd
c
a
n
he
lp
identi
f
y
tr
i
gge
r
s
or
a
s
s
oc
iation
s
with
s
pe
c
if
ic
a
c
ti
vit
ies
.
Ambulator
y
E
E
G
is
les
s
r
e
s
tr
ictive
than
inpatient
moni
tor
ing,
pr
omot
ing
pa
ti
e
nt
c
omf
or
t
a
nd
c
ompl
ianc
e
.
C
ons
:
Ambulato
r
y
E
E
G
r
e
c
or
dings
may
be
s
us
c
e
pti
ble
to
mot
ion
a
r
ti
f
a
c
ts
a
nd
e
nvir
onmenta
l
int
e
r
f
e
r
e
nc
e
,
a
f
f
e
c
ti
ng
da
ta
qua
l
it
y.
I
nte
r
pr
e
tation
of
a
mbul
a
tor
y
E
E
G
r
e
qui
r
e
s
e
xpe
r
ti
s
e
to
dif
f
e
r
e
nti
a
te
e
pil
e
pti
c
a
c
ti
vit
y
f
r
om
a
r
ti
f
a
c
ts
a
c
c
ur
a
tely.
T
he
dur
a
ti
on
o
f
a
mbul
a
tor
y
E
E
G
moni
t
or
ing
is
li
mi
ted,
a
nd
longer
moni
to
r
ing
pe
r
iods
may
be
ne
c
e
s
s
a
r
y
to
c
a
ptur
e
inf
r
e
que
nt
or
noc
tur
na
l
s
e
izur
e
s
.
F
igur
e
3
s
hows
that
ge
ne
r
a
li
z
e
d
e
pil
e
pti
c
s
e
izur
e
s
may
be
a
bs
e
nt
(
pe
ti
t
mal)
,
ton
ic
-
c
loni
c
(
gr
a
nd
mal)
,
a
toni
c
,
myoclonic,
c
loni
c
,
a
nd
toni
c
.
F
igur
e
3.
T
ype
s
a
nd
s
ubtypes
of
s
e
izur
e
s
2.
1.
4.
I
n
t
r
aop
e
r
at
ive
E
E
G:
I
n
t
r
aop
e
r
at
ive
E
E
G
is
r
e
c
or
de
d
du
r
ing
ne
ur
os
ur
gica
l
pr
oc
e
du
r
e
s
f
or
e
pil
e
ps
y,
s
uc
h
a
s
e
pil
e
ps
y
s
ur
ge
r
y
or
im
planta
ti
on
of
de
vice
s
li
ke
va
gus
ne
r
ve
s
ti
mul
a
t
or
s
or
de
e
p
b
r
a
in
s
ti
mul
a
to
r
s
.
I
t
he
lps
guide
the
s
ur
gica
l
pr
oc
e
dur
e
a
nd
e
ns
ur
e
that
c
r
it
ica
l
br
a
in
r
e
gions
a
r
e
not
dis
tur
be
d
du
r
ing
s
ur
ge
r
y
.
P
r
os
:
I
nt
r
a
ope
r
a
ti
ve
E
E
G
pr
ovides
r
e
a
l
-
ti
me
moni
tor
ing
of
br
a
in
a
c
ti
vit
y
dur
ing
ne
ur
os
ur
gica
l
p
r
oc
e
dur
e
s
f
or
e
pil
e
ps
y,
a
ll
owing
ne
ur
os
ur
ge
ons
to
loca
li
z
e
e
pil
e
ptogenic
z
one
s
a
c
c
ur
a
tely
a
nd
a
void
da
mage
to
c
r
it
ica
l
br
a
in
r
e
gions
.
I
t
he
lps
guide
s
ur
gica
l
r
e
s
e
c
ti
on
bounda
r
ies
a
nd
a
s
s
e
s
s
the
e
f
f
ica
c
y
of
int
e
r
ve
nti
ons
s
uc
h
a
s
c
or
ti
c
a
l
s
ti
mul
a
ti
on.
I
ntr
a
ope
r
a
ti
ve
E
E
G
c
a
n
pr
ovide
im
media
te
f
e
e
dba
c
k
on
the
e
f
f
e
c
ts
of
s
ur
gica
l
manipulations
,
f
a
c
il
it
a
ti
ng
int
r
a
ope
r
a
ti
ve
de
c
is
ion
-
making.
C
ons
:
I
nt
r
a
ope
r
a
t
ive
E
E
G
r
e
qui
r
e
s
s
pe
c
ialize
d
e
quipm
e
nt
a
nd
e
xp
e
r
ti
s
e
to
pe
r
f
or
m
a
nd
int
e
r
pr
e
t
in
the
ope
r
a
ti
ng
r
oom
s
e
tt
ing.
S
ur
gica
l
pr
oc
e
dur
e
s
a
nd
a
ne
s
thetics
c
a
n
a
f
f
e
c
t
E
E
G
s
ignals
,
c
ompl
ica
ti
ng
int
e
r
pr
e
tation
a
nd
r
e
duc
ing
s
ignal
qua
li
ty
.
I
ntr
a
ope
r
a
ti
ve
E
E
G
may
not
a
lwa
ys
c
or
r
e
late
with
pr
e
ope
r
a
ti
ve
f
indi
ngs
or
pos
toper
a
ti
ve
outco
mes
.
3.
RE
S
UL
T
S
AN
D
DI
S
CU
S
S
I
ON
3.
1.
Qu
an
t
it
a
t
ive
E
E
G
(
q
E
E
G)
Qua
nti
tative
E
E
G
invol
ve
s
the
a
na
lys
is
of
E
E
G
da
ta
us
ing
a
dva
nc
e
d
c
omput
a
ti
ona
l
tec
hniques
to
e
xtr
a
c
t
qua
nti
tative
mea
s
ur
e
s
of
b
r
a
in
a
c
ti
vit
y
.
I
t
pr
ovides
a
ddit
ional
in
f
or
mation
a
bout
br
a
in
f
unc
ti
on
a
nd
c
a
n
he
lp
loca
li
z
e
e
pil
e
ptogenic
z
one
s
a
nd
pr
e
d
ict
tr
e
a
tm
e
nt
outcome
s
.
P
r
os
:
qE
E
G
invol
ve
s
a
dva
nc
e
d
c
omput
a
ti
ona
l
E
E
G
da
ta
a
na
lys
is
,
pr
ovidi
ng
objec
ti
ve
mea
s
ur
e
s
of
b
r
a
in
a
c
ti
vit
y
a
nd
c
onne
c
ti
vit
y
.
I
t
e
na
bles
qua
nti
tative
a
s
s
e
s
s
ment
of
e
pil
e
pti
f
or
m
a
bnor
malit
ies
,
ne
twor
k
dyna
mi
c
s
,
a
nd
s
pa
ti
a
l
loca
li
z
a
ti
on
of
e
pil
e
ptogenic
z
one
s
.
qE
E
G
c
a
n
f
a
c
il
it
a
te
e
a
r
ly
d
e
tec
ti
on
of
e
pil
e
pti
c
a
c
ti
vit
y
a
nd
pr
e
diction
of
t
r
e
a
tm
e
nt
outcome
s
.
C
ons
:
qE
E
G
r
e
quir
e
s
s
pe
c
ialize
d
s
of
tw
a
r
e
a
nd
e
xpe
r
ti
s
e
to
a
c
c
ur
a
tely
pe
r
f
o
r
m
da
ta
a
na
l
ys
is
a
nd
int
e
r
pr
e
tation.
T
he
c
li
nica
l
uti
l
it
y
of
qE
E
G
metr
ic
s
may
va
r
y
de
pe
nding
on
pa
ti
e
nt
c
ha
r
a
c
ter
is
ti
c
s
,
e
lec
tr
ode
plac
e
ment,
a
nd
a
na
lys
is
tec
hnique
s
.
S
tanda
r
dizing
qE
E
G
pr
otocols
a
nd
va
li
da
ti
on
of
qua
nti
tative
mea
s
ur
e
s
a
r
e
ongoing
c
ha
ll
e
nge
s
.
T
he
a
bbr
e
viation
typi
c
a
ll
y
r
e
pr
e
s
e
nts
F
r
ontopol
a
r
(
F
P
1
,
F
P
2)
,
F
r
ontal
(
F
3,
F
4)
,
F
r
ontot
e
mpor
a
l
(
F
7
,
F
8)
,
C
e
ntr
a
l
(
C
3,
C
4)
,
T
e
mpor
a
l
(
T
3,
T
4
)
,
P
a
r
ieto
-
tempor
a
l
(
T
5,
T
6
)
,
P
a
r
ieta
l
(
P
3,
P
4)
,
Oc
c
ipi
tal
(
O1,
O2
)
,
T
im
e
(
HH
:M
M
:S
S
)
.
F
igur
e
4
s
hows
the
5
pa
ti
e
nts
'
E
E
G
a
na
lys
is
r
e
a
dings
.
EEG
-
ba
s
e
d
pa
ti
e
nt
s
tatus
e
s
a
r
e
de
picte
d
in
T
a
ble
s
1
to
5
,
e
a
c
h
s
hows
the
E
E
G
s
a
mpl
e
s
of
the
f
ir
s
t
to
f
i
f
th
pa
ti
e
nts
,
r
e
s
pe
c
ti
ve
ly.
T
he
notation
de
picts
a
c
onve
nti
ona
l
10
-
20
E
E
G
e
lec
tr
ode
plac
e
ment
method.
T
his
br
a
in
a
c
ti
vit
y
mapping
tec
hnique
is
uti
li
z
e
d
c
li
nica
ll
y
.
Odd
-
num
be
r
e
d
e
lec
tr
ode
s
a
r
e
plac
e
d
on
the
lef
t
s
ide
o
f
the
s
c
a
lp,
a
nd
e
ve
n
-
number
e
d
e
lec
tr
ode
s
a
r
e
on
the
r
ight
.
E
pil
e
ps
y
diagnos
is
a
nd
tr
e
a
tm
e
nt
typi
c
a
ll
y
inclu
de
E
E
G
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
1
4
,
No.
5
,
Oc
tober
2
02
4
:
6047
-
6056
6052
moni
tor
ing.
C
e
r
tain
br
a
in
e
lec
tr
ica
l
a
c
ti
vit
y
pa
tt
e
r
ns
may
s
ignal
e
pil
e
ps
y
o
r
a
s
s
is
t
in
diagnos
ing
i
t
on
the
E
E
G.
E
E
G
de
tec
ts
a
be
r
r
a
nt
br
a
in
e
lec
tr
ica
l
a
c
ti
vi
ty,
including
s
pikes
,
s
ha
r
p
wa
ve
s
,
a
nd
r
hythm
ic
pa
tt
e
r
ns
,
whic
h
diagnos
e
e
pil
e
pti
c
s
e
izur
e
s
.
E
E
G
mon
it
or
ing
ove
r
ti
me
he
lps
phys
icia
ns
dis
c
ove
r
a
typi
c
a
l
s
e
izur
e
pa
tt
e
r
ns
,
loca
te
the
br
a
in's
s
e
izur
e
c
a
us
e
,
a
nd
c
us
t
omi
z
e
tr
e
a
tm
e
nt
tec
hniques
.
E
E
G
he
lps
c
onf
ir
m
e
pil
e
ps
y,
identif
y
s
e
izur
e
types
,
guide
dr
ug
mana
ge
ment,
a
n
d
a
s
s
e
s
s
ther
a
py
e
f
f
ica
c
y.
F
igur
e
4.
P
a
ti
e
nt’
s
s
tatus
T
a
ble
1.
T
he
f
ir
s
t
p
a
ti
e
nt
’
s
E
E
G
s
a
mpl
e
s
T
im
e
(
in
hh
-
mm
-
ss)
F
P
2
-
F4
F
4
-
C4
C
4
-
P4
P
4
-
O2
F
P
2
-
F8
F
8
-
T4
T
4
-
T6
T
6
-
O2
F
P
1
-
F3
F
3
-
C3
C
3
-
P3
P
3
-
O1
F
P
1
-
F7
F
7
-
T3
T
3
-
T5
T
5
-
O1
00
-
00
-
01
14
-
57
2
1
38
-
46
-
83
52
-
33
-
28
-
39
64
-
65
-
30
54
5
00
-
00
-
02
19
-
48
0
14
43
-
41
-
89
71
-
44
-
26
-
25
62
-
81
-
24
69
2
00
-
00
-
03
22
-
35
-
4
24
43
-
38
-
72
73
-
54
-
34
-
14
72
-
72
-
33
68
8
00
-
00
-
04
58
-
20
-
4
44
76
-
31
-
56
88
-
32
-
25
-
6
85
-
38
-
34
78
17
00
-
00
-
05
40
-
26
-
19
56
60
-
47
-
60
96
-
57
-
29
-
17
93
-
72
-
37
84
16
T
a
ble
2.
T
he
s
e
c
ond
p
a
ti
e
nt’
s
E
E
G
s
a
mpl
e
s
T
im
e
(
in
hh
-
mm
-
ss)
F
P
2
-
F4
F
4
-
C4
C
4
-
P4
P
4
-
O2
F
P
2
-
F8
F
8
-
T4
T
4
-
T6
T
6
-
O2
F
P
1
-
F3
F
3
-
C3
C
3
-
P3
P
3
-
O1
F
P
1
-
F7
F
7
-
T3
T
3
-
T5
T
5
-
O1
00
-
04
-
05
11
-
9
-
1
6
6
-
2
0
3
0
-
1
5
2
-
5
5
2
3
00
-
04
-
06
2
-
3
-
4
-
3
2
-
4
-
10
5
13
-
2
-
6
1
9
-
8
7
-
1
00
-
04
-
07
0
0
-
2
-
5
3
-
4
12
-
18
-
13
2
1
-
6
-
4
-
6
-
6
0
00
-
04
-
08
4
-
9
-
5
6
0
-
10
-
1
7
-
3
0
-
2
2
-
4
-
4
-
3
7
00
-
04
-
09
-
3
1
2
-
2
-
1
0
-
3
1
-
8
5
-
1
-
8
-
5
-
3
-
3
0
T
a
ble
3.
T
he
thi
r
d
pa
ti
e
nt’
s
E
E
G
s
a
mpl
e
s
T
im
e
(
in
h
h
-
mm
-
ss)
F
P
2
-
F4
F
4
-
C4
C
4
-
P4
P
4
-
O2
F
P
2
-
F8
F
8
-
T4
T
4
-
T6
T
6
-
O2
F
P
1
-
F3
F
3
-
C3
C
3
-
P3
P
3
-
O1
F
P
1
-
F7
F
7
-
T3
T
3
-
T5
T
5
-
O1
00
-
02
-
01
130
-
64
-
82
175
121
14
-
58
82
41
119
-
110
21
15
-
176
131
100
00
-
02
-
02
122
117
-
249
227
122
-
64
75
84
55
-
27
31
-
74
-
81
113
-
33
-
14
00
-
02
-
03
161
-
9
-
113
82
59
100
-
137
99
-
25
98
-
124
41
-
178
214
-
161
115
00
-
02
-
04
-
7
9
86
-
50
147
-
50
-
66
7
-
91
57
-
45
-
19
-
192
96
50
-
52
00
-
02
-
05
-
34
26
-
143
66
-
113
-
95
300
-
177
-
37
161
19
-
19
68
59
-
75
71
T
a
ble
4.
T
he
f
our
th
pa
ti
e
nt’
s
E
E
G
s
a
mpl
e
s
T
im
e
(
in
hh
-
mm
-
ss)
F
P
2
-
F4
F
4
-
C4
C
4
-
P4
P
4
-
O2
F
P
2
-
F8
F
8
-
T4
T
4
-
T6
T
6
-
O2
F
P
1
-
F3
F
3
-
C3
C
3
-
P3
P
3
-
O1
F
P
1
-
F7
F
7
-
T3
T
3
-
T5
T
5
-
O1
00
-
00
-
41
-
18
-
150
323
-
2
-
211
260
-
130
239
305
-
440
157
-
20
22
-
92
-
111
136
00
-
00
-
42
152
103
-
172
148
86
64
-
41
122
178
307
-
153
-
165
2579
-
2387
32
-
56
00
-
00
-
43
-
94
182
-
174
112
-
93
-
34
75
79
374
-
93
-
71
-
155
140
182
-
49
-
218
00
-
00
-
44
-
249
174
-
233
377
-
118
109
-
83
162
99
729
-
967
561
50
31
78
263
-
3
0
0
-
2
0
0
-
1
0
0
0
100
200
300
400
0
0
-
0
0
-
0
1
0
0
-
0
4
-
0
9
0
0
-
0
0
-
4
4
0
0
-
0
0
-
5
9
I
n
Num
b
e
r
s
I
n
T
i
me
F
P
2
-
F
4
F
4
-
C4
C4
-
P
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
lec
&
C
omp
E
ng
I
S
S
N:
2088
-
8708
C
loud
bas
e
d
pr
e
diction
of
e
pil
e
pti
c
s
e
iz
ur
e
s
us
ing
r
e
al
-
ti
me
e
lec
tr
oe
nc
e
phalogr
am
s
…
(
Gous
ia
T
hah
niyath
)
6053
T
a
ble
5.
T
he
f
if
th
pa
ti
e
nt’
s
E
E
G
s
a
mpl
e
s
T
im
e
(
in
hh
-
mm
-
ss)
F
P
2
-
F4
F
4
-
C4
C
4
-
P4
P
4
-
O2
F
P
2
-
F8
F
8
-
T4
T
4
-
T6
T
6
-
O2
F
P
1
-
F3
F
3
-
C3
C
3
-
P3
P
3
-
O1
F
P
1
-
F7
F
7
-
T3
T
3
-
T5
T
5
-
O1
00
-
00
-
56
-
325
-
14
39
-
399
-
154
-
1047
913
-
411
458
360
4537
-
5020
188
400
-
810
557
00
-
00
-
57
193
-
7
-
438
394
-
60
-
54
-
39
295
-
282
72
437
-
122
284
-
457
107
172
00
-
00
-
58
250
-
86
-
7
-
201
345
-
431
-
7
49
-
490
194
400
154
112
21
-
6
132
00
-
00
-
59
303
287
-
52
-
233
486
-
320
182
-
43
-
215
271
-
633
316
66
145
-
517
45
00
-
01
-
00
-
137
-
218
-
442
690
-
492
315
-
68
138
270
126
-
510
229
-
273
272
288
-
172
3.
2.
S
ou
r
c
e
l
oc
ali
z
a
t
ion
E
E
G
T
his
tec
hnique
invol
ve
s
us
ing
a
dva
nc
e
d
im
a
ging
methods
to
loca
li
z
e
the
s
our
c
e
of
e
pil
e
pti
c
a
c
ti
vit
y
withi
n
the
br
a
in.
I
t
he
lps
identif
y
the
s
e
izur
e
ons
e
t
z
one
a
nd
plan
tar
ge
ted
int
e
r
ve
nti
ons
s
uc
h
a
s
s
ur
ge
r
y
o
r
f
oc
us
e
d
ne
ur
os
ti
mul
a
ti
on.
P
r
os
:
S
ou
r
c
e
loca
li
z
a
ti
on
E
E
G
invol
ve
s
a
dva
nc
e
d
i
maging
tec
hniques
t
o
loca
li
z
e
the
or
igi
n
of
e
pil
e
pti
c
a
c
ti
vit
y
withi
n
the
b
r
a
in,
pr
ovidi
ng
pr
e
c
is
e
a
na
tom
ica
l
loca
li
z
a
ti
on
a
nd
f
unc
ti
ona
l
mapping
of
e
pil
e
ptogenic
z
one
s
.
I
t
he
lps
guide
s
u
r
gica
l
planning,
opti
mi
z
e
e
lec
tr
ode
plac
e
ment,
a
n
d
pr
e
dict
s
ur
gica
l
outcome
s
.
S
ou
r
c
e
loca
li
z
a
ti
on
E
E
G
c
a
n
e
nha
nc
e
the
a
c
c
ur
a
c
y
a
nd
e
f
f
ica
c
y
of
e
pil
e
ps
y
s
ur
ge
r
y,
mi
nim
izing
the
r
is
k
o
f
ne
ur
ologi
c
a
l
de
f
icits
.
C
ons
:
S
our
c
e
loca
li
z
a
ti
on
E
E
G
r
e
qui
r
e
s
s
ophis
ti
c
a
ted
ne
ur
oim
a
ging
s
of
twa
r
e
a
nd
e
xpe
r
ti
s
e
to
a
c
c
ur
a
tely
pe
r
f
or
m
im
a
ge
pr
oc
e
s
s
ing,
s
our
c
e
r
e
c
ons
tr
uc
ti
on,
a
nd
int
e
r
pr
e
tation.
I
ts
c
li
nica
l
uti
li
ty
may
be
li
mi
ted
b
y
im
a
ge
r
e
s
olut
ion,
s
ignal
-
to
-
nois
e
r
a
ti
o,
a
nd
va
r
iabili
ty
in
s
our
c
e
loca
li
z
a
ti
on
a
lgor
i
thm
s
.
E
E
G
he
lps
c
onf
ir
m
e
pil
e
ps
y,
identif
y
s
e
izur
e
types
,
gu
ide
d
r
ug
mana
ge
ment,
a
nd
a
s
s
e
s
s
ther
a
py
e
f
f
ica
c
y.
3.
3.
S
lee
p
E
E
G
S
lee
p
E
E
G
is
pe
r
f
or
med
to
e
va
luate
b
r
a
in
a
c
ti
vit
y
dur
ing
s
lee
p,
a
s
s
e
izur
e
s
of
ten
oc
c
ur
du
r
ing
s
lee
p
or
a
r
e
in
f
luenc
e
d
by
s
lee
p
pa
tt
e
r
ns
.
I
t
he
lps
a
s
s
e
s
s
the
im
pa
c
t
of
s
lee
p
on
s
e
izur
e
a
c
ti
vi
ty
a
nd
identi
f
y
s
pe
c
if
ic
pa
tt
e
r
ns
a
s
s
oc
iate
d
with
s
le
e
p
-
r
e
late
d
s
e
izur
e
s
.
P
r
os
:
S
lee
p
E
E
G
pr
ov
ides
va
luable
inf
or
mation
a
bo
ut
br
a
in
a
c
ti
vit
y
dur
ing
di
f
f
e
r
e
nt
s
tage
s
of
s
lee
p,
a
s
s
e
izur
e
s
of
ten
oc
c
ur
o
r
a
r
e
in
f
luenc
e
d
by
s
lee
p
pa
tt
e
r
ns
.
I
t
he
lps
in
c
ha
r
a
c
ter
izing
s
lee
p
-
r
e
late
d
e
pil
e
pti
c
s
yndr
omes
a
nd
identif
ying
s
pe
c
if
ic
a
bnor
mali
ti
e
s
a
s
s
oc
iat
e
d
with
noc
tur
na
l
s
e
izur
e
s
.
S
lee
p
E
E
G
c
a
n
e
nha
nc
e
diagn
os
ti
c
yield
by
c
a
ptur
ing
s
e
izur
e
e
ve
nts
that
c
oinci
de
with
s
lee
p
.
C
ons
:
S
lee
p
E
E
G
r
e
quir
e
s
s
pe
c
ialize
d
e
qu
ipm
e
nt
a
nd
e
xpe
r
t
is
e
to
pe
r
f
or
m
a
nd
int
e
r
pr
e
t
a
c
c
ur
a
tely.
P
a
ti
e
nt
pr
e
pa
r
a
ti
on
f
or
s
lee
p
E
E
G
may
be
ti
me
-
c
ons
umi
ng,
a
nd
c
ompl
ianc
e
with
s
lee
p
de
pr
ivation
pr
otocols
c
a
n
be
c
ha
ll
e
nging.
S
lee
p
E
E
G
r
e
c
or
dings
may
be
s
us
c
e
pti
ble
to
a
r
ti
f
a
c
ts
r
e
late
d
to
s
lee
p
moveme
nts
or
e
nvir
onmenta
l
f
a
c
tor
s
.
4.
CONC
L
USI
ON
P
r
os
pe
c
ts
a
nd
obs
tac
les
a
bound
f
or
us
ing
c
loud
-
ba
s
e
d
r
e
a
l
-
ti
me
E
E
G
a
na
lys
is
in
s
e
izur
e
pr
e
diction.
S
e
ve
r
a
l
obs
tac
les
s
ti
ll
ne
e
d
to
be
ove
r
c
ome,
but
te
c
hnologi
c
a
l
pr
ogr
e
s
s
holds
s
ome
e
nc
our
a
ging
pos
s
ibi
li
ti
e
s
f
or
be
tt
e
r
s
e
izur
e
pr
e
diction
a
c
c
ur
a
c
y
a
nd
mor
e
r
a
pid
ther
a
pies
.
S
e
c
ur
e
ly
s
tor
ing
a
nd
p
r
oc
e
s
s
ing
s
e
ns
it
ive
pa
ti
e
nt
da
ta
on
c
loud
s
e
r
ve
r
s
is
the
bigges
t
obs
tac
le
s
ince
it
r
e
qui
r
e
s
s
tr
ong
e
nc
r
ypti
on
a
nd
a
dhe
r
e
nc
e
to
s
tr
ict
pr
ivac
y
s
tanda
r
ds
.
S
e
izur
e
pr
e
diction
s
ys
tems
'
r
e
a
l
-
ti
me
na
tur
e
may
be
c
ompr
omi
s
e
d
by
wor
r
i
e
s
a
bout
late
nc
y
a
nd
ne
twor
k
c
onne
c
ti
on
b
r
ought
a
bout
by
de
pe
nde
nc
e
on
c
loud
inf
r
a
s
tr
uc
tur
e
.
Als
o,
va
r
iou
s
pe
ople
a
nd
kinds
of
s
e
izur
e
s
pr
oduc
e
E
E
G
da
ta
that
a
r
e
c
ompl
ica
ted
a
nd
va
r
iable
,
whic
h
mi
ght
r
e
s
tr
ict
the
a
c
c
ur
a
c
y
of
the
pr
e
diction
models
.
T
he
de
ploym
e
nt
o
f
s
uc
h
s
ys
tems
mi
ght
ha
ve
a
s
ubs
tantial
e
f
f
e
c
t
,
im
pr
o
ving
the
qua
li
ty
of
li
f
e
f
or
e
pil
e
ps
y
pa
ti
e
nts
via
tailor
e
d
tr
e
a
tm
e
nt
methods
a
nd
lowe
r
ing
the
f
r
e
que
nc
y
a
nd
s
e
ve
r
it
y
of
s
e
izur
e
s
,
notwit
hs
tanding
thes
e
li
mi
tations
.
T
his
s
e
c
ti
on
dis
c
us
s
e
s
the
r
e
s
ult
s
f
r
o
m
f
ive
s
e
pa
r
a
te
da
t
a
s
e
ts
of
pa
ti
e
nts
with
e
pil
e
pti
c
s
e
izur
e
s
who
unde
r
we
nt
E
E
G
a
na
lys
is
with
the
f
oll
owing
de
tails
a
s
F
r
ontopol
a
r
(
F
P
1
,
F
P
2)
,
F
r
ontal
(
F
3
,
F
4)
,
F
r
ontot
e
mpo
r
a
l
(
F
7,
F
8
)
,
C
e
ntr
a
l
(
C
3,
C
4)
,
T
e
mpor
a
l
(
T
3,
T
4)
,
P
a
r
ieto
-
tempor
a
l
(
T
5,
T
6)
,
P
a
r
ieta
l
(
P
3
,
P
4
)
,
Oc
c
ipi
tal
(
O1
,
O2)
,
T
im
e
(
H
H:M
M
:S
S
)
.
RE
F
E
RE
NC
E
S
[
1]
G
. Y
oga
r
a
ja
n
e
t
al
.
, “
E
E
G
-
ba
s
e
d e
pi
le
pt
ic
s
e
iz
ur
e
de
te
c
ti
on us
in
g bi
na
r
y dr
a
gonf
ly
a
lg
or
it
hm
a
nd de
e
p ne
ur
a
l
ne
twor
k,”
Sc
ie
nt
if
ic
R
e
por
ts
, vol
. 13, no. 1, Oc
t.
2023, doi:
10.1038/s
41598
-
023
-
44318
-
w.
[
2]
M
.
H
.
A
ls
h
a
ye
ji
,
“
C
A
D
s
y
s
te
m
f
or
e
pi
le
pt
ic
s
e
iz
ur
e
de
t
e
c
ti
on
f
r
om
E
E
G
th
r
ough
im
a
ge
pr
oc
e
s
s
in
g
a
nd
S
U
R
F
-
B
O
F
te
c
hni
q
ue
,”
M
ac
hi
ne
L
e
ar
ni
ng:
Sc
ie
nc
e
and T
e
c
hnol
ogy
, vol
. 4, no. 4, D
e
c
.
2023, doi:
10.1088/2632
-
2153/a
d0572.
[
3]
Z
.
L
a
s
e
f
r
,
K
.
E
ll
e
it
hy,
R
.
R
.
R
e
ddy,
E
.
A
bde
lf
a
tt
a
h,
a
nd
M
.
F
a
e
z
ip
our
,
“
A
n
e
pi
le
pt
ic
s
e
iz
ur
e
de
te
c
ti
on
te
c
hni
que
u
s
in
g
E
E
G
s
ig
na
ls
w
it
h
mobi
le
a
ppl
ic
a
ti
on
de
v
e
lo
pme
nt
,”
A
ppl
ie
d
Sc
ie
nc
e
s
(
Sw
it
z
e
r
la
nd)
,
vol
.
13,
no.
17,
p.
9571,
A
ug.
2023,
doi
:
10.3390/a
pp13179571.
[
4]
A
.
A
.
E
in
S
hoka
,
M
.
M
.
D
e
s
s
ouky,
A
.
E
l
-
S
a
ye
d,
a
nd
E
.
E
.
D
. H
e
mda
n,
“
E
E
G
s
e
iz
ur
e
de
te
c
ti
on:
c
onc
e
pt
s
,
te
c
hni
qu
e
s
,
c
h
a
ll
e
n
ge
s
,
a
nd
f
ut
ur
e
tr
e
nds
,”
M
ul
ti
m
e
di
a
T
ool
s
and
A
ppl
ic
at
io
ns
,
vol
.
8
2,
no.
27,
pp.
42021
–
42051,
N
ov.
2023,
doi
:
10.1007/s
11042
-
023
-
15052
-
2.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
1
4
,
No.
5
,
Oc
tober
2
02
4
:
6047
-
6056
6054
[
5]
K
.
A
nj
um
a
nd
D
.
P
ompi
li
,
“
A
ni
s
ot
r
opi
c
di
f
f
us
io
n
-
ba
s
e
d a
na
lo
g
C
N
N
a
r
c
hi
te
c
tu
r
e
f
or
c
ont
in
uous
E
E
G
moni
to
r
in
g,”
in
2023
I
E
E
E
20t
h
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on
M
obi
le
A
d
H
oc
an
d
Sm
ar
t
Sy
s
te
m
s
(
M
A
SS)
,
S
e
p.
2023,
pp.
195
–
203,
doi
:
10.1109/M
A
S
S
58611.2023.00031.
[
6]
A
.
B
.
K
.
R
e
t
a
l.
,
“
A
m
ul
t
i
-
d
im
e
n
s
io
n
a
l
h
ybr
id
C
N
N
-
B
iL
S
T
M
f
r
a
m
e
w
or
k
f
or
e
p
il
e
pt
i
c
s
e
i
z
ur
e
d
e
te
c
ti
o
n
u
s
in
g
e
le
c
t
r
o
e
n
c
e
p
h
a
lo
gr
a
m
s
i
gn
a
l
s
c
r
u
ti
ny
,”
S
y
s
t
e
m
s
an
d
So
ft
C
om
pu
ti
ng
,
vo
l.
5
,
p.
2
00
06
2,
D
e
c
.
20
23
,
doi
:
10
.1
01
6/
j.
s
a
s
c
.
20
23
.2
00
06
2.
[
7]
S
.
S
r
in
iv
a
s
a
n,
S
.
D
a
ya
la
ne
,
S
.
K
uma
r
M
a
th
iv
a
na
n,
H
.
R
a
ja
dur
a
i,
P
.
J
a
ya
gopa
l,
a
nd
G
.
T
.
D
a
lu
,
“
D
e
te
c
ti
on
a
nd
c
la
s
s
if
ic
a
ti
on
of
a
dul
t
e
pi
le
ps
y
u
s
in
g
hybr
id
de
e
p
l
e
a
r
ni
ng
a
ppr
oa
c
h,”
Sc
ie
nt
if
ic
R
e
por
ts
,
vol
.
13,
no.
1,
O
c
t.
2023,
doi
:
10.1038/s
41598
-
0
23
-
44763
-
7.
[
8]
S
.
L
e
nka
la
,
R
.
M
a
r
r
y,
S
.
R
.
G
opova
r
a
m,
T
.
C
.
A
ki
nc
i,
a
nd
O
.
T
ops
a
ka
l,
“
C
ompa
r
is
on
of
a
ut
oma
te
d
ma
c
hi
ne
le
a
r
ni
ng
(
A
ut
oM
L
)
to
ol
s
f
or
e
pi
le
pt
ic
s
e
iz
ur
e
de
te
c
ti
on
us
in
g
e
le
c
tr
oe
nc
e
pha
lo
gr
a
ms
(
E
E
G
)
,”
C
om
put
e
r
s
,
vol
.
12,
no.
10,
p.
197,
S
e
p.
2023,
doi
:
10.3390/c
omput
e
r
s
12100197.
[
9]
B
. J
a
is
ha
nka
r
, A
. M
. A
s
hw
in
i,
D
. V
id
ya
bha
r
a
th
i,
a
nd L
. R
a
ja
, “
A
nove
l
e
pi
le
ps
y s
e
iz
ur
e
pr
e
di
c
ti
on mode
l
us
in
g de
e
p l
e
a
r
ni
ng
a
nd
c
la
s
s
if
ic
a
ti
on,”
H
e
al
th
c
ar
e
A
nal
y
ti
c
s
, vol
. 4, p. 100222, D
e
c
. 20
23, doi:
10.1016/j
.he
a
lt
h.2023.100222.
[
10]
A
. L
. N
. A
l
-
ha
jj
a
r
a
nd A
. K
. M
. A
l
-
Q
ur
a
ba
t,
“
A
n ove
r
vi
e
w
of
ma
c
hi
ne
l
e
a
r
ni
ng me
th
ods
i
n e
na
bl
in
g I
oM
T
-
ba
s
e
d e
pi
le
pt
ic
s
e
i
z
ur
e
de
te
c
ti
on,”
J
our
nal
of
Supe
r
c
om
put
in
g
, vol
. 79, no. 14, pp. 160
17
–
16064, S
e
p. 2023, doi:
10.1007/s
11227
-
023
-
05299
-
9.
[
11]
A
.
L
a
te
e
f
N
oor
A
l
-
ha
jj
a
r
a
nd
A
.
K
a
dhum
M
.
A
l
-
Q
ur
a
ba
t1
,
“
E
pi
le
pt
ic
s
e
iz
ur
e
de
te
c
ti
on
us
in
g
f
e
a
tu
r
e
im
por
ta
nc
e
a
nd
M
L
c
la
s
s
if
ie
r
s
,”
J
our
nal
of
E
duc
at
io
n f
or
P
ur
e
Sc
ie
n
c
e
-
U
ni
v
e
r
s
it
y
of
T
hi
-
Q
ar
, vol
. 13, no. 2, 2023, doi
:
10.32792/j
e
ps
.v13i2.310.
[
12]
S
.
S
a
mi
nu
e
t
al
.
,
“
A
ppl
ic
a
ti
ons
of
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
in
a
ut
o
ma
ti
c
de
te
c
ti
on
of
e
pi
le
pt
ic
s
e
iz
ur
e
s
us
in
g
E
E
G
s
ig
na
ls
:
a
r
e
vi
e
w
,”
A
r
ti
fi
c
ia
l
I
nt
e
ll
ig
e
nc
e
and A
ppl
ic
at
io
ns
, vol
. 1, no. 1, pp. 11
–
25
, 2022, doi:
10.47852/bonvi
e
w
a
ia
2202297.
[
13]
N
.
M
c
C
a
ll
a
n
e
t
al
.
,
“
E
pi
le
pt
ic
mul
ti
-
s
e
iz
ur
e
ty
pe
c
l
a
s
s
if
ic
a
ti
o
n
us
in
g
e
le
c
tr
oe
n
c
e
pha
lo
gr
a
m
s
ig
n
a
ls
f
r
om
th
e
T
e
mpl
e
U
ni
ve
r
s
it
y
H
os
pi
ta
l
S
e
iz
ur
e
C
or
pus
:
A
r
e
vi
e
w
,”
E
x
pe
r
t
Sy
s
t
e
m
s
w
it
h A
ppl
i
c
at
io
ns
, vol
. 234, 2023, doi:
10.1016/j
.e
s
w
a
.2023.121040.
[
14]
R
.
K
r
is
hna
V
a
na
k
a
ma
mi
di
,
L
.
R
a
ma
li
nga
m,
N
.
A
bi
r
a
mi
,
S
.
P
r
iy
a
nka
,
C
.
S
.
K
uma
r
,
a
nd
S
.
M
ur
uga
n,
“
I
oT
s
e
c
ur
it
y
ba
s
e
d
on
ma
c
hi
ne
le
a
r
ni
ng,”
in
2023
Se
c
ond
I
nt
e
r
nat
io
nal
C
onf
e
r
e
n
c
e
on
Sm
ar
t
T
e
c
hnol
ogi
e
s
fo
r
S
m
ar
t
N
at
io
n
(
Sm
ar
tT
e
c
hC
on)
,
A
ug.
2023, pp. 683
–
687, doi:
10.1109/S
ma
r
tT
e
c
hC
on57526.2023.10391727.
[
15]
T
.
R
.
S
a
r
a
va
na
n,
A
.
R
.
R
a
th
in
a
m,
J
.
L
e
ni
n,
A
.
K
oma
th
i,
B
.
B
ha
r
a
th
i,
a
nd
S
.
M
ur
uga
n,
“
R
e
vol
ut
io
ni
z
in
g
c
lo
ud
c
omput
i
ng:
e
va
lu
a
ti
ng
th
e
in
f
lu
e
nc
e
of
bl
oc
kc
h
a
in
a
nd
c
ons
e
ns
us
a
lg
or
it
hms
,”
in
2023
3r
d
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
Sm
a
r
t
G
e
ne
r
at
io
n
C
om
put
in
g,
C
om
m
uni
c
at
io
n
and
N
e
tw
o
r
k
in
g,
SM
A
R
T
G
E
N
C
O
N
2023
,
D
e
c
.
2023,
pp.
1
–
6,
doi
:
10.1109/S
M
A
R
T
G
E
N
C
O
N
60755.2023.10442008.
[
16]
C
. H
. C
ha
ndr
a
S
e
kha
r
, K
. V
ij
a
ya
la
ks
hmi
, A
. S
a
nya
s
i
R
a
o, V
. V
e
da
na
r
a
ya
na
n, M
. B
. S
a
ha
a
i,
a
nd S
. M
ur
uga
n, “
C
lo
ud
-
ba
s
e
d w
a
te
r
ta
nk
ma
na
ge
me
nt
a
nd
c
ont
r
ol
s
ys
t
e
m,”
in
2023
2nd
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
Sm
a
r
t
T
e
c
hnol
ogi
e
s
fo
r
S
m
ar
t
N
at
io
n,
Sm
ar
tT
e
c
hC
on 2023
, A
ug. 2023, pp. 641
–
646, doi:
10.1109/S
ma
r
tT
e
c
hC
on57526.2023.10391730.
[
17]
Y
. Y
a
ng, J
. K
. E
s
hr
a
ghi
a
n, N
. D
uy T
r
uong, A. N
ik
pour
, a
nd O
. K
a
ve
he
i,
“
N
e
ur
omor
phi
c
de
e
p s
pi
ki
ng ne
ur
a
l
ne
twor
ks
f
or
s
e
i
z
ur
e
de
te
c
ti
on,”
N
e
u
r
om
or
phi
c
C
om
put
in
g and E
ngi
ne
e
r
in
g
, vol
. 3,
no. 1, 2023, doi:
10.1088/2634
-
4386/a
c
ba
b8.
[
18]
O
.
M
.
A
s
s
im
a
nd
A
.
F
.
M
a
hmood,
“
D
e
s
ig
ni
ng
a
w
e
a
r
a
bl
e
E
E
G
de
vi
c
e
a
nd
it
s
be
ne
f
it
s
f
or
e
pi
le
ps
y
pa
ti
e
nt
s
:
a
r
e
vi
e
w
,”
Al
-
K
it
ab
J
our
nal
f
or
P
ur
e
Sc
i
e
nc
e
s
, vol
. 7, no. 1, pp. 69
–
82, 2023, doi:
1
0.32441/kj
ps
.07.01.p7.
[
19]
S
.
J
a
ha
n
e
t
al
.
,
“
A
I
-
B
a
s
e
d
E
pi
le
pt
ic
S
e
iz
ur
e
D
e
te
c
ti
on
a
nd
P
r
e
di
c
ti
on
in
I
nt
e
r
ne
t
of
H
e
a
lt
hc
a
r
e
T
hi
ng
s
:
A
S
ys
te
ma
ti
c
R
e
vi
e
w
,”
I
E
E
E
A
c
c
e
s
s
, vol
. 11, pp. 30690
–
30725, 2023, doi:
10.1109/AC
C
E
S
S
.2023.3251105.
[
20]
N
.
K
uma
r
i,
U
.
T
iwa
r
i,
S
.
T
r
ip
a
th
i,
R
.
P
r
iy
a
da
r
s
hi
ni
,
a
nd
S
.
N
a
z
,
“
L
e
ve
r
a
gi
ng
w
e
a
r
a
bl
e
s
e
n
s
or
s
a
nd
s
up
e
r
vi
s
e
d
l
e
a
r
ni
ng
pa
r
a
d
ig
m
a
s
a
c
onf
ig
ur
a
bl
e
s
ol
ut
io
n
f
or
e
pi
le
pt
ic
pa
ti
e
nt
s
,”
I
nt
e
r
nat
io
nal
J
our
nal
of
C
om
put
in
g
and
D
ig
it
al
Sy
s
te
m
s
,
vol
.
14,
no.
1,
pp. 10243
–
10250, Oc
t.
2023, doi:
10.12785/i
jc
ds
/1
40197.
[
21]
A
.
S
in
gh,
V
.
R
.
V
e
la
ga
la
,
T
.
K
uma
r
,
R
.
R
.
D
ut
ta
,
a
nd
T
.
S
ont
a
kke
,
“
T
he
a
ppl
ic
a
ti
on
of
de
e
p
le
a
r
ni
ng
to
e
le
c
tr
oe
nc
e
pha
lo
gr
a
ms
,
ma
gne
ti
c
r
e
s
ona
nc
e
im
a
gi
ng,
a
nd
im
pl
a
nt
s
f
or
th
e
de
te
c
ti
on
of
e
pi
le
pt
ic
s
e
iz
ur
e
s
:
a
na
r
r
a
ti
ve
r
e
vi
e
w
,”
C
ur
e
us
,
J
ul
.
2023,
doi
:
10.7759/c
ur
e
us
.42460.
[
22]
A
.
S
a
ma
nt
a
,
I
.
H
a
t
a
i,
a
nd
A
.
K
.
M
a
l,
“
D
e
s
ig
n
a
n
E
E
c
ie
nt
F
P
G
A
ba
s
e
d
ha
r
dw
a
r
e
im
pl
e
me
nt
a
ti
on
f
or
r
e
a
l
-
ti
me
mobi
le
e
pi
l
e
pt
ic
s
e
iz
ur
e
pr
e
di
c
ti
on
u
s
in
g
de
e
p
n
e
ur
a
l
ne
twor
k
de
s
ig
n
a
n
e
f
f
ic
ie
nt
F
P
G
A
ba
s
e
d
ha
r
dw
a
r
e
im
pl
e
me
nt
a
ti
on
f
or
r
e
a
l
-
ti
me
mo
bi
le
e
pi
le
pt
ic
s
e
iz
ur
e
pr
e
di
c
ti
on us
in
g de
e
p ne
ur
a
l
ne
t,
”
P
r
e
pr
in
t:
R
e
s
e
a
r
c
h
S
qua
r
e
,
2023, doi:
10.21203/r
s
.3.r
s
-
1819772/v1.
[
23]
C
.
R
a
c
ha
pp
a
,
M
.
K
a
pa
n
a
ia
h,
a
nd
V
.
N
a
ga
r
a
ju
,
“
H
ybr
id
e
ns
e
mbl
e
le
a
r
ni
ng
f
r
a
me
w
or
k
f
or
e
pi
le
pt
ic
s
e
iz
ur
e
de
te
c
ti
on
us
in
g
e
le
c
tr
oe
nc
e
pha
lo
gr
a
ph
s
ig
na
ls
,
”
I
ndone
s
ia
n
J
ou
r
nal
of
E
l
e
c
tr
ic
al
E
ngi
ne
e
r
in
g
and
C
om
put
e
r
Sc
ie
n
c
e
,
vol
.
28,
no
.
3,
pp. 1502
–
1509, 2022, doi:
10.11591/i
je
e
c
s
.v28.i3.pp1502
-
1509.
[
24]
S
. I
. S
a
f
ie
, P
.
Z
. M
. K
ha
li
d, a
nd M
. A
im
ul
la
h, “
M
ode
li
ng pha
s
mophobi
a
(
f
e
a
r
of
ghos
ts
)
us
in
g e
le
c
tr
oe
nc
e
pha
lo
gr
a
m,”
I
ndone
s
ia
n
J
our
nal
of
E
le
c
tr
ic
al
E
ngi
ne
e
r
in
g
and
C
om
put
e
r
Sc
ie
nc
e
,
vol
.
26,
no.
2,
pp.
743
–
753,
M
a
y
2022,
doi
:
10.11591/i
je
e
c
s
.v26.i2.pp743
-
753.
[
25]
D
.
H
.
E
lk
a
mc
houc
hi
,
A
.
D
.
A
lg
a
r
ni
,
R
.
M
.
G
honi
e
m,
a
nd
H
.
G
.
M
oha
me
d,
“
A
de
e
p
le
a
r
ni
ng
s
ig
ne
d
me
di
c
a
l
im
a
ge
ba
s
e
d
on
c
r
ypt
ogr
a
phi
c
te
c
hni
que
s
,”
I
ndone
s
ia
n
J
our
nal
of
E
le
c
t
r
ic
al
E
ngi
ne
e
r
in
g
and
C
om
put
e
r
Sc
ie
n
c
e
,
vol
.
29,
no.
1,
pp.
481
–
495,
J
a
n.
2023, doi:
10.11591/i
je
e
c
s
.v29.i1.pp481
-
495.
[
26]
J
.
O
uc
hr
if
,
A
.
B
a
ghda
d,
A
.
S
a
he
l,
a
nd
A
.
B
a
dr
i,
“
H
ig
h
-
pe
r
f
or
ma
nc
e
I
nP
/I
n
G
a
A
s
he
te
r
oj
unc
ti
on
bi
pol
a
r
pho
to
tr
a
ns
is
to
r
s
f
or
opt
oe
le
c
tr
oni
c
a
ppl
ic
a
ti
ons
,”
I
ndone
s
ia
n
J
our
nal
of
E
le
c
tr
ic
al
E
ngi
ne
e
r
in
g
and
C
om
put
e
r
Sc
ie
nc
e
,
vol
.
32,
no.
1,
pp.
80
–
89,
O
c
t.
2023, doi:
10.11591/i
je
e
c
s
.v32.i1.pp80
-
89.
[
27]
M
.
S
unka
r
a
a
nd
R
.
S
.
R
a
ja
kuma
r
i,
“
P
r
e
di
c
ti
on
of
th
e
e
pi
le
pt
ic
s
e
iz
ur
e
th
r
ough
de
e
p
le
a
r
ni
ng
te
c
hni
que
s
u
s
in
g
e
le
c
tr
oe
nc
e
pha
lo
gr
a
phy,”
I
ndone
s
ia
n
J
our
nal
of
E
le
c
t
r
ic
al
E
ngi
ne
e
r
in
g
and
C
om
put
e
r
Sc
ie
n
c
e
,
vol
.
32,
no.
2,
pp.
1123
–
11
33,
N
ov. 2023, doi:
10.11591/i
je
e
c
s
.v32.i2.pp1123
-
1133.
[
28]
R
.
R
a
ma
n,
S
.
M
ut
huma
r
il
a
ks
hmi
,
G
.
J
e
th
a
va
,
R
.
J
a
gt
a
p,
M
.
L
a
li
th
a
,
a
nd
S
.
M
ur
uga
n,
“
E
ne
r
gy
moni
to
r
in
g
in
s
ol
a
r
-
pow
e
r
e
d
bui
ld
in
gs
us
in
g
in
te
r
ne
t
o
f
th
in
gs
,”
in
2023
2nd
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
Sm
ar
t
T
e
c
hnol
ogi
e
s
fo
r
Sm
ar
t
N
at
io
n,
Sm
ar
tT
e
c
hC
on 2023
, A
ug. 2023, pp. 318
–
322, doi:
10.1109/S
ma
r
tT
e
c
hC
on57526.2023.10391826.
[
29]
V
.
G
.
S
iv
a
kuma
r
,
V
.
V
.
B
a
s
ka
r
,
M
.
V
a
di
ve
l,
S
.
P
.
V
im
a
l,
a
nd
S
.
M
ur
uga
n,
“
I
oT
a
nd
G
I
S
in
te
gr
a
ti
on
f
or
r
e
a
l
-
ti
me
moni
to
r
in
g
of
s
oi
l
he
a
lt
h
a
nd
nut
r
ie
nt
s
ta
tu
s
,”
in
2023
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
S
e
lf
Sus
ta
in
abl
e
A
r
ti
fi
c
ia
l
I
nt
e
ll
ig
e
nc
e
Sy
s
te
m
s
(
I
C
SSA
S)
,
O
c
t.
2023, pp. 1265
–
1270, doi:
10.1109/I
C
S
S
A
S
57918.2023.1
0331694.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
lec
&
C
omp
E
ng
I
S
S
N:
2088
-
8708
C
loud
bas
e
d
pr
e
diction
of
e
pil
e
pti
c
s
e
iz
ur
e
s
us
ing
r
e
al
-
ti
me
e
lec
tr
oe
nc
e
phalogr
am
s
…
(
Gous
ia
T
hah
niyath
)
6055
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
Go
us
i
a
Tha
hn
i
y
a
th
i
s
an
as
s
i
s
t
an
t
p
r
o
fes
s
o
r
at
t
h
e
D
ep
art
me
n
t
o
f
Co
mp
u
t
er
Sci
en
ce
a
n
d
E
n
g
i
n
eeri
n
g
,
D
ay
a
n
an
d
a
Sa
g
ar
U
n
i
v
ers
i
t
y
,
Ban
g
al
o
re.
G
o
u
s
i
a
T
h
ah
n
i
y
at
h
h
a
s
co
mp
l
et
e
d
h
er
P
h
.
D
.
fro
m
V
i
s
v
es
w
aray
a
T
ech
n
o
l
o
g
i
ca
l
U
n
i
v
ers
i
t
y
.
H
er
area
o
f
res
e
arch
i
s
rel
at
e
d
t
o
w
i
re
l
es
s
s
en
s
o
r
n
et
w
o
r
k
s
.
Sh
e
h
as
co
mp
l
et
e
d
h
er
M.
E
.
i
n
co
mp
u
t
er
s
ci
e
n
ce
an
d
en
g
i
n
eer
i
n
g
fro
m
Ban
g
al
o
re
U
n
i
v
ers
i
t
y
an
d
h
er
B.
E
.
i
n
co
mp
u
t
er
s
ci
e
n
ce
an
d
en
g
i
n
eeri
n
g
fro
m
G
u
l
b
arg
a
U
n
i
v
er
s
i
t
y
.
S
h
e
h
a
s
1
6
y
ears
o
f
t
eac
h
i
n
g
ex
p
eri
e
n
ce
an
d
h
as
o
n
e
y
ear
o
f
i
n
d
u
s
t
ri
al
e
x
p
er
i
en
ce.
Sh
e
h
as
p
u
b
l
i
s
h
ed
p
ap
er
s
i
n
7
i
n
t
ern
at
i
o
n
al
j
o
u
rn
a
l
s
a
n
d
h
as
p
res
e
n
t
e
d
p
ap
er
s
at
i
n
t
ern
a
t
i
o
n
al
an
d
n
at
i
o
n
al
c
o
n
fere
n
ces
.
Sh
e
can
b
e
co
n
t
act
e
d
at
emai
l
:
g
o
u
s
i
a
-
cs
e@
d
s
u
.
ed
u
.
i
n
.
C
hel
l
ub
o
i
n
a
Subba
r
a
y
udu
Ga
n
g
a
i
a
h
Y
a
da
v
i
s
cu
rren
t
l
y
w
o
rk
i
n
g
as
an
as
s
o
ci
a
t
e
p
r
o
fes
s
o
r
o
f
E
CE
a
t
Ch
a
i
t
a
n
y
a
B
h
arat
h
i
I
n
s
t
i
t
u
t
e
o
f
T
ech
n
o
l
o
g
y
,
Pr
o
d
d
at
u
r.
H
e
h
a
s
1
2
y
ears
o
f
ex
p
eri
e
n
ce
i
n
t
eac
h
i
n
g
.
H
e
d
i
d
an
M.
T
ech
.
i
n
s
p
ec
i
al
i
zat
i
o
n
V
L
SI
s
y
s
t
em
d
es
i
g
n
an
d
a
f
u
rt
h
er
Ph
.
D
.
i
n
t
h
e
s
ame
d
i
s
c
i
p
l
i
n
e.
H
i
s
b
ro
ad
fi
e
l
d
o
f
res
e
arch
w
as
V
L
SI
an
d
E
mb
e
d
d
e
d
Sy
s
t
ems
.
H
i
s
areas
o
f
i
n
t
eres
t
i
n
c
l
u
d
e
V
L
SI
emb
ed
d
e
d
s
y
s
t
em
s
an
d
Io
T
.
H
e
h
a
s
p
u
b
l
i
s
h
ed
res
earc
h
p
a
p
ers
i
n
b
o
t
h
i
n
t
er
n
at
i
o
n
al
a
n
d
n
at
i
o
n
al
j
o
u
r
n
al
s
o
f
re
p
u
t
e.
H
e
h
a
s
p
u
b
l
i
s
h
ed
p
a
t
en
t
s
a
n
d
a
l
s
o
p
u
b
l
i
s
h
e
d
a
b
o
o
k
.
H
e
a
l
s
o
s
er
v
es
a
s
t
h
e
N
A
A
C
an
d
N
B
A
Co
o
rd
i
n
at
o
r.
H
e
i
s
a
memb
er
o
f
t
ech
n
i
ca
l
s
o
ci
e
t
i
e
s
l
i
k
e
IE
T
E
,
IST
E
,
ISRD
,
a
n
d
I
A
E
N
G
.
H
e
h
as
o
rg
a
n
i
ze
d
w
o
rk
s
h
o
p
s
an
d
w
eb
i
n
ar
s
at
a
n
a
t
i
o
n
a
l
l
e
v
el
.
H
e
h
a
s
s
er
v
ed
a
s
a
re
v
i
e
w
er
fo
r
Sco
p
u
s
-
i
n
d
ex
e
d
j
o
u
rn
a
l
s
.
H
e
ca
n
b
e
co
n
t
ac
t
ed
a
t
g
an
g
ai
ah
h
.
ece@
cb
i
t
.
ed
u
.
i
n
.
R
a
j
a
g
o
pa
l
a
n
Senk
a
m
a
l
a
v
a
l
l
i
i
s
c
u
rren
t
l
y
w
o
rk
i
n
g
as
a
Pro
fe
s
s
o
r,
D
e
p
art
me
n
t
o
f
In
fo
rma
t
i
o
n
Sc
i
en
ce
a
n
d
E
n
g
i
n
eer
i
n
g
,
A
MC
E
n
g
i
n
e
eri
n
g
Co
l
l
eg
e
,
Ban
g
al
o
re,
K
ar
n
at
a
k
a,
In
d
i
a.
Sh
e
h
as
1
5
Y
ears
o
f
t
each
i
n
g
ex
p
er
i
en
ce
i
n
co
m
p
u
t
er
s
ci
e
n
ce
en
g
i
n
eer
i
n
g
s
u
b
j
ec
t
s
.
Sh
e
h
as
p
u
b
l
i
s
h
ed
a
b
o
o
k
o
n
ar
t
i
f
i
ci
a
l
i
n
t
e
l
l
i
g
e
n
ce
a
n
d
e
x
p
er
t
s
y
s
t
ems
.
S
h
e
h
a
s
a
t
t
e
n
d
e
d
2
0
s
emi
n
ars
a
n
d
p
res
e
n
t
e
d
man
y
p
a
p
ers
a
t
n
a
t
i
o
n
a
l
an
d
i
n
t
e
rn
a
t
i
o
n
a
l
co
n
feren
ce
s
.
Sh
e
h
a
s
p
u
b
l
i
s
h
ed
man
y
p
ap
er
s
i
n
n
at
i
o
n
al
a
n
d
i
n
t
er
n
at
i
o
n
al
j
o
u
r
n
al
s
.
Sh
e
i
s
a
reci
p
i
e
n
t
o
f
t
h
e
Pres
i
d
en
t
A
w
ar
d
i
n
G
i
rl
s
G
u
i
d
e.
Sh
e
can
b
e
co
n
t
ac
t
ed
at
i
d
-
d
r.
r
s
en
k
amal
a
v
al
l
i
@
k
s
i
t
.
ed
u
.
i
n
.
S
h
a
n
m
u
g
a
m
S
a
th
i
y
a
P
r
i
y
a
i
s
c
u
rr
e
n
t
l
y
w
o
r
k
i
n
g
a
s
a
p
r
o
f
e
s
s
o
r
i
n
t
h
e
D
e
p
a
r
t
m
e
n
t
o
f
E
C
E
a
t
P
a
n
i
m
a
l
a
r
I
n
s
t
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
C
h
e
n
n
a
i
.
S
h
e
o
b
t
a
i
n
e
d
h
e
r
P
h
.
D
.
f
r
o
m
Sa
t
h
y
a
b
a
m
a
U
n
i
v
e
r
s
i
t
y
,
h
e
r
m
a
s
t
e
r’
s
d
e
g
re
e
w
i
t
h
h
o
n
o
r
s
i
n
c
o
mm
u
n
i
c
a
t
i
o
n
s
y
s
t
em
s
f
r
o
m
T
h
i
a
g
a
ra
j
ar
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
M
a
d
u
r
a
i
,
a
n
d
h
er
b
ac
h
e
l
o
r
’
s
d
e
g
r
e
e
i
n
e
l
e
c
t
r
o
n
i
c
s
a
n
d
c
o
m
m
u
n
i
ca
t
i
o
n
e
n
g
i
n
e
er
i
n
g
f
r
o
m
M
o
h
a
me
d
Sa
t
h
a
k
E
n
g
i
n
e
er
i
n
g
C
o
l
l
e
g
e
,
K
i
l
a
k
ar
a
i
,
a
ff
i
l
i
a
t
e
d
w
i
t
h
Ma
d
u
ra
i
K
a
m
ar
a
j
U
n
i
v
e
r
s
i
t
y
,
Ma
d
u
ra
i
.
S
h
e
h
a
s
p
u
b
l
i
s
h
e
d
2
5
p
a
p
ers
i
n
i
n
t
er
n
a
t
i
o
n
a
l
a
n
d
n
a
t
i
o
n
a
l
j
o
u
r
n
a
l
s
a
n
d
3
2
p
a
p
er
s
i
n
n
a
t
i
o
n
a
l
c
o
n
f
er
e
n
c
e
s
.
H
e
r
ar
ea
s
o
f
i
n
t
er
e
s
t
i
n
c
l
u
d
e
w
i
re
l
e
s
s
c
o
m
m
u
n
i
c
a
t
i
o
n
,
U
W
B
c
o
mm
u
n
i
ca
t
i
o
n
,
a
n
d
c
h
a
n
n
e
l
e
s
t
i
ma
t
i
o
n
.
S
h
e
h
a
s
m
o
re
t
h
a
n
2
3
y
e
ar
s
o
f
t
ea
c
h
i
n
g
e
x
p
e
r
i
e
n
ce.
S
h
e
h
a
s
a
t
t
e
n
d
e
d
1
5
s
h
o
rt
-
t
er
m
c
o
u
r
s
e
s
,
a
t
t
e
n
d
e
d
3
0
s
em
i
n
ar
s
,
w
o
r
k
s
h
o
p
s
,
a
n
d
F
D
P
s
,
a
n
d
o
r
g
a
n
i
ze
d
s
e
m
i
n
a
r
s
a
n
d
w
o
r
k
s
h
o
p
s
r
e
l
a
t
e
d
t
o
h
e
r
a
re
a
o
f
r
e
s
e
ar
c
h
.
S
h
e
i
s
o
n
e
o
f
t
h
e
a
u
t
h
o
r
s
o
f
t
h
e
books
T
r
a
n
s
m
i
s
s
i
o
n
L
i
n
e
s
a
n
d
W
a
v
e
g
u
i
d
es
a
n
d
I
n
t
e
g
r
a
t
e
d
C
i
r
c
u
i
t
s
A
p
p
l
i
c
a
t
i
o
n
s
T
u
n
a
b
l
e
D
i
o
d
e
a
n
d
P
h
o
t
o
n
i
c
s
.
S
h
e
i
s
a
l
i
fe
m
em
b
e
r
i
n
IS
T
E
.
S
h
e
c
a
n
b
e
c
o
n
t
ac
t
e
d
a
t
s
a
t
h
i
y
a
p
r
i
y
a.
a
n
b
u
n
a
t
h
a
n
@
g
m
a
i
l
.
c
o
m
.
Sta
l
i
n
A
g
ha
l
y
a
i
s
p
res
e
n
t
l
y
w
o
rk
i
n
g
as
an
as
s
o
c
i
at
e
p
ro
fe
s
s
o
r
i
n
t
h
e
E
CE
D
ep
ar
t
men
t
,
at
St
.
J
o
s
ep
h
’
s
Co
l
l
eg
e
o
f
E
n
g
i
n
eeri
n
g
,
Ch
en
n
ai
.
Sh
e
h
as
p
u
r
s
u
e
d
h
er
fu
l
l
-
t
i
me
Ph
.
D
.
fro
m
A
n
n
a
U
n
i
v
er
s
i
t
y
,
In
d
i
a.
Sh
e
recei
v
e
d
h
er
M.
E
.
(O
p
t
i
ca
l
co
mmu
n
i
ca
t
i
o
n
)
i
n
2
0
0
2
fro
m
CE
G
,
A
n
n
a
U
n
i
v
er
s
i
t
y
,
C
h
en
n
ai
,
a
n
d
h
er
B.
E
.
(E
l
ect
r
o
n
i
cs
a
n
d
c
o
mmu
n
i
cat
i
o
n
en
g
i
n
eer
i
n
g
)
i
n
1
9
9
1
fr
o
m
T
PG
IT
,
V
el
l
o
re.
H
er
re
s
e
arch
i
n
t
ere
s
t
s
are
w
i
re
l
e
s
s
n
e
t
w
o
rk
s
,
mo
b
i
l
e
n
et
w
o
r
k
s
,
an
d
d
i
g
i
t
a
l
i
mag
e
p
ro
ce
s
s
i
n
g
.
Sh
e
h
as
mo
re
t
h
a
n
2
3
y
ears
o
f
t
each
i
n
g
ex
p
er
i
en
ce.
Sh
e
can
b
e
co
n
t
ac
t
ed
at
a
g
h
a
l
y
a
7
0
@
g
ma
i
l
.
c
o
m.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2088
-
8708
I
nt
J
E
lec
&
C
omp
E
ng
,
Vol
.
1
4
,
No.
5
,
Oc
tober
2
02
4
:
6047
-
6056
6056
Kuppi
reddy
N
a
r
s
i
m
ha
R
edd
y
recei
v
ed
t
h
e
Ph
.
D
.
D
eg
ree
i
n
E
C
E
fro
m
K
L
E
F,
A
P
i
n
2
0
2
3
,
an
d
t
h
e
M.
T
ec
h
.
d
eg
ree
i
n
V
L
SI
d
es
i
g
n
fro
m
t
h
e
V
i
g
an
a
n
U
n
i
v
ers
i
t
y
,
A
P,
In
d
i
a,
i
n
2
0
1
1
,
an
d
t
h
e
B.
T
ec
h
.
d
eg
r
ee
i
n
el
ec
t
ro
n
i
c
s
an
d
co
m
mu
n
i
cat
i
o
n
en
g
i
n
eeri
n
g
fr
o
m
J
N
T
U
H
U
n
i
v
er
s
i
t
y
,
H
y
d
erab
a
d
,
In
d
i
a,
i
n
2
0
0
9
.
H
i
s
res
earch
i
n
t
e
res
t
s
i
n
c
l
u
d
e
s
i
g
n
a
l
p
ro
ce
s
s
i
n
g
,
i
mag
e
p
ro
ce
s
s
i
n
g
,
an
d
V
L
SI
d
es
i
g
n
.
H
e
h
as
p
u
b
l
i
s
h
ed
1
3
res
earch
p
ap
er
s
i
n
v
ari
o
u
s
i
n
t
ern
a
t
i
o
n
a
l
j
o
u
rn
a
l
s
an
d
co
n
fere
n
ces
.
Pres
en
t
l
y
h
e
i
s
w
o
rk
i
n
g
as
an
as
s
i
s
t
an
t
p
ro
fes
s
o
r
i
n
t
h
e
D
e
p
art
me
n
t
o
f
E
CE
,
V
ard
h
aman
Co
l
l
e
g
e
o
f
E
n
g
i
n
eeri
n
g
,
H
y
d
era
b
a
d
,
T
el
a
n
g
a
n
a.
H
e
can
b
e
co
n
t
ac
t
ed
a
t
s
i
mh
a.
v
ce@
v
ard
h
aman
.
o
rg
.
Subbi
a
h
M
urug
a
n
i
s
a
n
a
d
j
u
n
c
t
p
r
o
fes
s
o
r
a
t
Sa
v
ee
t
h
a
Sc
h
o
o
l
o
f
E
n
g
i
n
eeri
n
g
,
Sav
eet
h
a
In
s
t
i
t
u
t
e
o
f
Med
i
cal
an
d
T
ec
h
n
i
cal
Sc
i
en
ce
s
,
Ch
en
n
ai
,
T
ami
l
N
a
d
u
,
I
n
d
i
a.
H
e
p
u
b
l
i
s
h
ed
h
i
s
res
earc
h
art
i
cl
e
s
i
n
man
y
i
n
t
er
n
at
i
o
n
al
a
n
d
n
at
i
o
n
al
c
o
n
fere
n
ces
a
n
d
j
o
u
rn
a
l
s
.
H
i
s
re
s
earch
areas
i
n
c
l
u
d
e
n
et
w
o
r
k
s
ecu
r
i
t
y
an
d
mach
i
n
e
l
ear
n
i
n
g
.
H
e
can
b
e
c
o
n
t
act
e
d
at
s
mu
re
s
j
u
r@
g
mai
l
.
co
m.
Evaluation Warning : The document was created with Spire.PDF for Python.